© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 116775
    Prev
    Next
    INDEX
    Explanations

    sections related to substances or materials described in detail or involved in processes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     للاسماء
    -0.76
    IntoConstraints
    -0.66
    tagHelperRunner
    -0.64
    ValueStyle
    -0.64
     ModelExpression
    -0.57
    دانشنامهٔ
    -0.57
    rungsseite
    -0.56
    Життєпис
    -0.55
    ]")]
    -0.55
    awtextra
    -0.54
    POSITIVE LOGITS
    rickson
    0.34
    VersionUID
    0.31
     nemici
    0.30
     mourut
    0.30
    SOCK
    0.30
    humanité
    0.29
    miyorum
    0.29
     specimen
    0.29
     oseb
    0.29
     removed
    0.29
    Activations Density 0.034%

    No Known Activations