© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10921
    Prev
    Next
    INDEX
    Explanations

    elements related to online interaction and community feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Actions related to online content (share, report, flag)

    np_acts-logits-general · gemini-2.0-flash

    user<MAX_ACTIVATING_TOKENS>PostPostpostedPostPostPostedPostpostPostPostpostAdd</MAX_ACTIVATING_TOKENS><TOKENS_AFTER_MAX_ACTIVATING_TOKEN>byonbyonbyonbyonbyonbyon</TOKENS_AFTER_MAX_ACTIVATING_TOKEN><TOP_POSITIVE_LOGITS>onaddpostedPostpostaddtoand</TOP_POSITIVE_LOGITS><TOP_ACTIVATING_TEXTS>Post byonPost byonPost byonPost byonPost byonPost byonI have seen many posts on this topic and I myself am quite new to. My main question is how I can get one of the posts to show up with out me actually posting on here myself.I have seen many posts on this topic and I myself am quite new to. My main question is how I can get one of the posts to show up with out me actually posting on here myself.I've been trying to add a google calendar to my other calendars but it doesn't seem to work like it used to a few years ago.I have been reading a lot of posts about this subject lately and I was wondering if I can apply some of the principles to my situation.</TOP_ACTIVATING_TEXTS>Explain the neuron above with a word or phrase, not a complete sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onViewCreated
    -0.64
    aksanaan
    -0.59
     initWithFrame
    -0.59
    globalData
    -0.56
    stretchr
    -0.55
    antMatchers
    -0.54
    RetentionPolicy
    -0.52
     comprends
    -0.50
     cherchez
    -0.50
    Zapraszamy
    -0.50
    POSITIVE LOGITS
    
    0.72
    Show
    0.65
     »
    0.63
    Share
    0.63
     <<<<<<<<<<<<<<
    0.62
    View
    0.61
     View
    0.58
     ».
    0.58
     view
    0.57
     Show
    0.56
    Activations Density 1.265%

    No Known Activations