© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 54258
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ConstraintMaker
    -2.33
     ModelExpression
    -0.61
    createCanvas
    -0.60
    MigrationBuilder
    -0.56
    getRuntime
    -0.52
    snp
    -0.50
     ingenieros
    -0.43
     initComponents
    -0.40
    WritableDatabase
    -0.40
    DoubleQuotes
    -0.39
    POSITIVE LOGITS
    ModelAdmin
    2.06
    scrapy
    1.97
    Literatura
    1.00
    APIView
    0.95
     layui
    0.67
    Література
    0.63
     ExecuteAsync
    0.62
    layui
    0.55
    endpush
    0.53
    htbp
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.