Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1581
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and experiences

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

    Followed by a form of "to be"

    np_acts-logits-general · gemini-2.0-flash

    "I am" or "I was" forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.65
     "..\..\
    -0.56
     snippetHide
    -0.52
    
    -0.50
     "..\..\..\
    -0.50
     rocz
    -0.49
    IBOutlet
    -0.48
    featureID
    -0.47
    SwingConstants
    -0.46
    
    -0.46
    POSITIVE LOGITS
     fiquei
    0.89
     highly
    0.77
     ficou
    0.71
     extremely
    0.68
     agak
    0.65
     freaked
    0.64
     صوتيه
    0.63
    有点
    0.62
     Highly
    0.62
     terribly
    0.61
    Activations Density 0.255%

    No Known Activations