© 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. 53316
    Prev
    Next
    INDEX
    Explanations

    occurrences of underscores and their context in programming or buffer overflow discussions

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

    code delimiters and identifiers

    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
     humaines
    -0.40
    canActivate
    -0.38
     humanas
    -0.36
     lipat
    -0.35
     féminine
    -0.35
     organisée
    -0.35
     circulación
    -0.34
     aérienne
    -0.34
    ьажоргаш
    -0.33
     cocinar
    -0.33
    POSITIVE LOGITS
    _
    0.83
    \_
    0.78
     _
    0.72
    >_
    0.71
    (_
    0.68
    [_
    0.66
    /_
    0.65
    _/
    0.65
    }_
    0.65
     ._
    0.65
    Activations Density 0.016%

    No Known Activations