© 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. 105211
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and function calls in programming language text

    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
    transQ
    -0.63
     defStyle
    -0.57
     onPostExecute
    -0.57
     JpaRepository
    -0.57
    にほんブログ村
    -0.57
     TextInputType
    -0.57
     ujednoznacz
    -0.56
     HasFactory
    -0.56
     SPM
    -0.56
    TargetException
    -0.55
    POSITIVE LOGITS
     cuota
    0.33
    contentLoaded
    0.33
    COMPLETED
    0.31
     majd
    0.30
     RESID
    0.29
     发表于
    0.28
     plomo
    0.28
     They
    0.28
    FINISH
    0.27
    using
    0.27
    Activations Density 0.008%

    No Known Activations