© 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. 107489
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation related to programming and XML schemas

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

    Factory before Impl

    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
     ویکی‌پدی
    -0.73
    GEBURTS
    -0.71
    randomUUID
    -0.65
    tvguidetime
    -0.63
    LookAnd
    -0.61
    CloseOperation
    -0.60
     useAppContext
    -0.59
    toMatchSnapshot
    -0.59
    AntiForgeryToken
    -0.59
    parsedMessage
    -0.58
    POSITIVE LOGITS
     Simultaneously
    0.36
     simultaneously
    0.36
     Together
    0.36
    UpdatedAt
    0.35
     Đồng
    0.35
    SubCategory
    0.34
     ibid
    0.34
    代わりに
    0.34
    ต่อ
    0.33
     Füßen
    0.33
    Activations Density 0.001%

    No Known Activations