© 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. 24064
    Prev
    Next
    INDEX
    Explanations

    specific quantitative measurements or percentages related to food composition

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

    percentage content

    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
     surla
    -0.53
     utafitiHapana
    -0.50
    athione
    -0.50
    Half
    -0.45
    Rhestr
    -0.45
     Half
    -0.44
    RTLR
    -0.44
    .*")]
    -0.43
    Fordítás
    -0.43
    Personensuche
    -0.42
    POSITIVE LOGITS
     percentage
    0.85
     content
    0.79
     percent
    0.78
     percentages
    0.69
     (%)
    0.69
     %
    0.68
    percentage
    0.67
     Percent
    0.67
    content
    0.66
     \%
    0.66
    Activations Density 0.143%

    No Known Activations