Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56589
    Prev
    Next
    INDEX
    Explanations

    concepts related to food, particularly in the context of culinary arts and nutrition

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

    politics, power, defense, oil, photographs

    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
    findpost
    -0.52
     հղումներ
    -0.51
     '\\;'
    -0.47
    참고
    -0.46
     Obtén
    -0.45
     surla
    -0.45
    AlterField
    -0.44
     '{@
    -0.44
     prins
    -0.43
    ็จ
    -0.43
    POSITIVE LOGITS
    zungs
    0.46
    windowFixed
    0.39
     actuators
    0.37
    fromCharCode
    0.36
     ब्रेकडाउन
    0.36
     atheists
    0.35
     طریق
    0.35
    новниш
    0.35
    :✨
    0.35
    endmodule
    0.35
    Activations Density 0.124%

    No Known Activations