© 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 EvalsExportsAPI 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. 113346
    Prev
    Next
    INDEX
    Explanations

    references to data structures in programming contexts

    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
    NSIndexPath
    -1.73
    AtIndexPath
    -0.52
    NSNumber
    -0.46
    NSError
    -0.35
    ņa
    -0.32
    acı
    -0.31
    NSUserDefaults
    -0.29
    NSDate
    -0.28
    auto
    -0.28
    IZONTAL
    -0.28
    POSITIVE LOGITS
     IndexPath
    2.97
     lenker
    1.91
     препратки
    0.90
    Personensuche
    0.88
     ब्रेकडाउन
    0.77
    Viited
    0.77
     صوتيه
    0.76
     HasFactory
    0.76
    EndInit
    0.73
     initComponents
    0.72
    Activations Density 0.000%

    No Known Activations