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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 4206
    Prev
    Next
    INDEX
    Explanations

    web addresses and contact information

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

    URLs and website addresses

    np_acts-logits-general · gemini-2.0-flash

    urls and email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.65
    +#+#
    -0.62
    IsPostBack
    -0.57
    InjectAttribute
    -0.56
    UserScript
    -0.55
     nød
    -0.55
     teck
    -0.54
     opérateur
    -0.54
    сылкі
    -0.51
    IPAC
    -0.51
    POSITIVE LOGITS
     www
    1.22
    www
    1.12
    Www
    0.68
     WWW
    0.65
    wea
    0.63
    WWW
    0.61
    wwww
    0.59
    Visit
    0.56
    visit
    0.56
    mmas
    0.55
    Activations Density 0.111%

    No Known Activations