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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23569
    Prev
    Next
    INDEX
    Explanations

    references to parentheses and brackets in text

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

    parentheses and brackets

    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
    findpost
    -0.63
    writeFieldEnd
    -0.45
    Хьажоргаш
    -0.44
    Personensuche
    -0.40
    RenderAtEndOf
    -0.40
     Native
    -0.36
    ApiOperation
    -0.34
     كومونز
    -0.33
    揄
    -0.33
    Native
    -0.33
    POSITIVE LOGITS
     brackets
    1.02
     parenthesis
    0.94
    brackets
    0.91
     bracket
    0.88
    bracket
    0.88
     parentheses
    0.86
     Bracket
    0.85
    Bracket
    0.83
     brack
    0.82
    Brackets
    0.79
    Activations Density 0.086%

    No Known Activations