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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7366
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to function definitions and method calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arcilla
    -0.39
    mäßigen
    -0.31
    mäßige
    -0.30
     bolí
    -0.30
    ův
    -0.29
     acrylique
    -0.28
    mäß
    -0.28
     ſta
    -0.27
     její
    -0.26
     hydrauli
    -0.25
    POSITIVE LOGITS
    paymentMethod
    0.64
    numberOf
    0.64
    outputFile
    0.63
    expectedResult
    0.63
    addTo
    0.62
    checkOut
    0.62
    createTable
    0.62
    noOf
    0.62
    waitFor
    0.62
    toBe
    0.62
    Activations Density 2.540%

    No Known Activations