© 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. 31-GEMMASCOPE-RES-131K
    11. 90721
    Prev
    Next
    INDEX
    Explanations

    references to mechanical components and their functional interactions

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

    standing upright

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蚪
    -0.39
    AddTagHelper
    -0.38
     Infórmanos
    -0.37
     Exactos
    -0.36
     torchvision
    -0.35
    */].
    -0.35
     gran
    -0.35
    原始内容存档
    -0.35
    EXTERN
    -0.34
    ?></
    -0.34
    POSITIVE LOGITS
     upright
    0.95
     debout
    0.91
     stand
    0.88
     standing
    0.87
     berdiri
    0.86
     Standing
    0.84
     Stand
    0.82
    自立
    0.82
    Standing
    0.79
     STAND
    0.77
    Activations Density 0.030%

    No Known Activations