© 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. 20-GEMMASCOPE-RES-131K
    11. 50391
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to programming and software development

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

    dimensions and geometry

    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
    出版年
    -0.80
    featureID
    -0.75
    expandindo
    -0.74
    tvguidetime
    -0.73
    parsedMessage
    -0.72
    <unused47>
    -0.71
    <unused17>
    -0.71
    <unused23>
    -0.71
    <unused14>
    -0.71
    <unused8>
    -0.71
    POSITIVE LOGITS
    Dimensions
    0.90
     Dimensions
    0.88
     dimensions
    0.79
    dimensions
    0.70
     Dimensiones
    0.66
    Dimensiones
    0.63
     dimensiones
    0.57
    Dimension
    0.54
     DIMENSIONS
    0.54
     Dimension
    0.54
    Activations Density 0.001%

    No Known Activations