© 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. 105239
    Prev
    Next
    INDEX
    Explanations

    references to generalizations about people, relationships, and social issues

    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
    aarrggbb
    -0.53
    prepareStatement
    -0.47
    IGraphics
    -0.46
    awtextra
    -0.45
    ParallelGroup
    -0.43
     Sequelize
    -0.40
    ✭✭
    -0.40
    اریخ
    -0.40
    neté
    -0.39
     مشين
    -0.38
    POSITIVE LOGITS
     الرياضيه
    0.54
    ußen
    0.47
    thansa
    0.40
    ➟
    0.39
     Audiodateien
    0.39
     trasc
    0.38
     <=",
    0.38
    집
    0.37
    ViewFeatures
    0.37
    assic
    0.36
    Activations Density 0.056%

    No Known Activations