© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104766
    Prev
    Next
    INDEX
    Explanations

    relationships among numerical data points, emphasizing comparisons and statistical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     surla
    -0.83
    Tembelea
    -0.74
    Hochspringen
    -0.73
     queſta
    -0.73
    tagHelperRunner
    -0.68
    RenderAtEndOf
    -0.68
    rungsseite
    -0.67
     ProtoMessage
    -0.66
     للمعارف
    -0.66
    ConverterFactory
    -0.66
    POSITIVE LOGITS
    <?
    0.33
    ujud
    0.32
    ه
    0.31
    ẵn
    0.31
    <
    0.29
    a
    0.29
     less
    0.29
    へ
    0.28
     null
    0.28
     nearly
    0.27
    Activations Density 0.099%

    No Known Activations