© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2941
    Prev
    Next
    INDEX
    Explanations

    code structure and definitions in a programming context

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

    access modifier keywords and visibility declarations in code (private, public, readonly).

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    outdir
    -0.37
    GetList
    -0.34
     lname
    -0.32
     userid
    -0.30
     outfile
    -0.29
    getdata
    -0.28
     onclick
    -0.28
     roomId
    -0.27
    gettime
    -0.26
     mostly
    -0.25
    POSITIVE LOGITS
    RegressionTest
    0.96
    AccessorTable
    0.96
     wireType
    0.92
    OGND
    0.83
     للمعارف
    0.80
    featureID
    0.79
    EndContext
    0.78
    UnitTesting
    0.77
    KommentareTeilen
    0.76
     Infór
    0.75
    Activations Density 0.621%

    No Known Activations