© 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. 9-GEMMASCOPE-RES-131K
    11. 96310
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation marks, especially periods, in a code snippet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    method chaining delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desmotivaciones
    -1.02
    transQ
    -0.97
     $_(
    -0.97
     queſta
    -0.95
    ロウィン
    -0.94
     indígen
    -0.93
     increí
    -0.93
    linawan
    -0.91
     Verſ
    -0.90
    majánló
    -0.90
    POSITIVE LOGITS
    .
    0.65
     .
    0.47
    ->
    0.43
     be
    0.43
    ().
    0.43
    以
    0.41
    ::
    0.41
     to
    0.40
    に
    0.40
     “
    0.39
    Activations Density 0.008%

    No Known Activations