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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 40843
    Prev
    Next
    INDEX
    Explanations

    discrepancies related to legal verdicts and statistical disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     bassin
    -0.36
    a
    -0.35
    e
    -0.35
    IS
    -0.34
     CR
    -0.34
     Specification
    -0.33
     ход
    -0.33
    呼
    -0.33
     Experiments
    -0.32
    AS
    -0.32
    POSITIVE LOGITS
    ConstraintMaker
    0.63
     nahilalakip
    0.59
    ----</
    0.58
    findpost
    0.58
     مرئيه
    0.55
    aarrggbb
    0.54
    Халык
    0.52
     ویکی‌پدی
    0.52
    şört
    0.52
    Demografía
    0.50
    Activations Density 0.043%

    No Known Activations