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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45435
    Prev
    Next
    INDEX
    Explanations

    function declarations and calls in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    期刊论文
    -0.53
    UrlResolution
    -0.47
    Datuak
    -0.42
    MigrationBuilder
    -0.40
     iNdEx
    -0.38
    readdir
    -0.38
     <<<<<<<<<<<<<<
    -0.34
    leyici
    -0.34
     مشين
    -0.33
    MarshalTo
    -0.33
    POSITIVE LOGITS
    出版年
    0.59
     nahilalakip
    0.49
    berdayakan
    0.48
     onPostExecute
    0.47
    FieldBuilder
    0.45
    getProject
    0.44
    PreExecute
    0.43
    webElement
    0.43
    YNAMIC
    0.42
    quíni
    0.41
    Activations Density 0.112%

    No Known Activations