© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 13743
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InvalidProtocol
    -0.41
    sizeCache
    -0.40
     المرجع
    -0.38
    illoin
    -0.38
     dominate
    -0.37
    깐
    -0.36
     taxpayer
    -0.35
    पया
    -0.35
     groove
    -0.34
     sepanjang
    -0.34
    POSITIVE LOGITS
    migrations
    2.41
    Migrations
    1.08
     migrations
    1.04
    migrationBuilder
    1.02
     Migration
    0.94
     Mig
    0.90
    migration
    0.89
    Migration
    0.89
     migration
    0.86
    Mig
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.