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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117344
    Prev
    Next
    INDEX
    Explanations

    processes and results related to scientific studies or experiments

    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
    省市镇
    -0.58
    HtmlAttribute
    -0.53
     Roskov
    -0.53
    ंदीखरीदारी
    -0.52
    MessageOf
    -0.50
    RectangleBorder
    -0.49
    IBOutlet
    -0.49
    MLLoader
    -0.49
    migrationBuilder
    -0.49
    EndInit
    -0.48
    POSITIVE LOGITS
     réservé
    0.43
    aarrggbb
    0.42
     wet
    0.41
    ElementException
    0.39
     Treff
    0.39
    Preparación
    0.36
     depressed
    0.36
     הזה
    0.35
     así
    0.35
     flesta
    0.35
    Activations Density 0.113%

    No Known Activations