© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105071
    Prev
    Next
    INDEX
    Explanations

    dialogues and conversational interactions

    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
     виправивши
    -0.90
     gyhoeddwyd
    -0.88
    MigrationBuilder
    -0.78
    __":
    -0.77
    migrationBuilder
    -0.77
     ویکی‌پدی
    -0.75
     Italijanski
    -0.75
    featureID
    -0.74
     ModelExpression
    -0.73
     ProtoMessage
    -0.73
    POSITIVE LOGITS
     pitié
    0.31
    /
    0.30
     détermination
    0.28
    Vì
    0.28
     Karlsson
    0.27
     uzak
    0.26
    ீ
    0.26
     hierro
    0.26
     whenever
    0.26
     do
    0.25
    Activations Density 0.007%

    No Known Activations