© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 9838
    Prev
    Next
    INDEX
    Explanations

    patterns related to programming language syntax and structure

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ModelExpression
    -0.57
    Engineers
    -0.48
    SharedCtor
    -0.46
    %)$
    -0.45
    SuppressLint
    -0.45
    🟤
    -0.44
    Dsl
    -0.44
     fint
    -0.44
    ovia
    -0.43
    usermodel
    -0.41
    POSITIVE LOGITS
    msg
    0.76
     msg
    0.75
    msgSender
    0.68
     address
    0.64
    address
    0.64
    isContained
    0.61
     linkovi
    0.61
    RectangleBorder
    0.55
    vatar
    0.54
    bleshooting
    0.54
    Activations Density 0.093%

    No Known Activations