© 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. 104797
    Prev
    Next
    INDEX
    Explanations

    programming-related concepts and function declarations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    bootstrapcdn
    -0.73
    KommentareTeilen
    -0.68
    ValueStyle
    -0.66
    contentLoaded
    -0.64
     wireType
    -0.63
    ConstraintMaker
    -0.60
    rungsseite
    -0.59
    ChildScrollView
    -0.55
    <unused52>
    -0.55
    <unused14>
    -0.55
    POSITIVE LOGITS
     Children
    0.34
     active
    0.31
     police
    0.31
     ativa
    0.30
     region
    0.29
     able
    0.28
    Portail
    0.28
     piłkarz
    0.28
    Acti
    0.28
     régions
    0.28
    Activations Density 0.006%

    No Known Activations