Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 5303
    Prev
    Next
    INDEX
    Explanations

    expressions denoting a significant quantity or degree

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

    so much followed by

    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
     GetEnumerator
    -0.46
    CustomAttributes
    -0.44
    qtype
    -0.42
    駆け
    -0.37
    Proto
    -0.35
    typen
    -0.35
     principios
    -0.35
    結果は
    -0.35
     AUTHOR
    -0.34
    lind
    -0.34
    POSITIVE LOGITS
     zoveel
    0.69
    VersionUID
    0.63
     المعيارى
    0.58
    __(/*!
    0.57
     tantas
    0.54
     EVERYTHING
    0.54
    那么多
    0.54
    这么多
    0.53
    Everything
    0.52
    anganese
    0.52
    Activations Density 0.006%

    No Known Activations