© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 105478
    Prev
    Next
    INDEX
    Explanations

    compiler warning directives and associated diagnostics in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.77
     Administrativna
    -0.73
    UserScript
    -0.68
    mergeFrom
    -0.68
    SharedCtor
    -0.67
    SharedDtor
    -0.66
    InitVars
    -0.64
    ngdoc
    -0.63
    Parcelize
    -0.63
     useAppContext
    -0.61
    POSITIVE LOGITS
     warning
    0.93
    Warning
    0.77
    warning
    0.76
     Warning
    0.75
     WARNING
    0.69
    WARNING
    0.68
     warnings
    0.67
    Warnings
    0.60
    warnings
    0.59
     warn
    0.55
    Activations Density 0.002%

    No Known Activations