© 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. 8556
    Prev
    Next
    INDEX
    Explanations

    references to programming structures and object-oriented terminology

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    self.emit

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ToProps
    -0.39
    .*")]
    -0.38
    例文帳に追加
    -0.36
     péri
    -0.36
     NSCoder
    -0.36
    Билгалдахарш
    -0.35
     genom
    -0.35
    RotationOrder
    -0.34
     getRule
    -0.33
    
    -0.30
    POSITIVE LOGITS
    AnchorStyles
    0.57
    IntoConstraints
    0.53
    insegna
    0.51
    phors
    0.50
    MENAFN
    0.46
     lẫn
    0.46
    MigrationBuilder
    0.46
     uſed
    0.45
    ptest
    0.44
    帖最后由
    0.44
    Activations Density 0.013%

    No Known Activations