© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 21141
    Prev
    Next
    INDEX
    Explanations

    mentions of statistics, research findings, and classifications related to art and agriculture

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

    quantities of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     few
    -0.46
     fairly
    -0.43
     نسب
    -0.42
     certain
    -0.42
     particularly
    -0.42
     Audiodateien
    -0.41
     sein
    -0.41
     robust
    -0.39
     modest
    -0.39
     minimal
    -0.38
    POSITIVE LOGITS
     ribuan
    0.59
     MainAxisSize
    0.50
    parsedMessage
    0.49
    thousands
    0.47
    全世界
    0.47
     Infórmanos
    0.46
     thousands
    0.46
     Thousands
    0.45
    PDOException
    0.43
    !”.
    0.43
    Activations Density 0.077%

    No Known Activations