© 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. 107398
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols

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

    which finishes or matches

    np_acts-logits-general · gemini-2.5-flash-lite

    words that serve as discourse/connective signals (function words like "we", "which", "by", "so") in formal/mathematical text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     Italij
    -0.54
    ⓧ
    -0.47
    脚注の使い方
    -0.46
    󠁢
    -0.46
    ISupport
    -0.44
     '\\;'
    -0.43
    webElementGuid
    -0.43
     незавершена
    -0.42
    AndEndTag
    -0.42
     uParam
    -0.42
    POSITIVE LOGITS
    Subviews
    0.47
    PMailer
    0.44
    lama
    0.39
    QLabel
    0.38
    BIA
    0.38
    gründ
    0.38
     spar
    0.37
    NewGuid
    0.37
    iring
    0.37
    ia
    0.37
    Activations Density 0.828%

    No Known Activations