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. 103122
    Prev
    Next
    INDEX
    Explanations

    keywords and identifiers used in programming and coding contexts

    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
    dafx
    -0.59
    CloseOperation
    -0.52
    rawDesc
    -0.47
    StructEnd
    -0.47
     ویکی‌پدیا
    -0.44
    RectangleBorder
    -0.43
    UrlEncoded
    -0.40
     оригіналу
    -0.40
     EconPapers
    -0.39
    htbp
    -0.39
    POSITIVE LOGITS
    pantalon
    0.48
    ThroughAttribute
    0.47
    bluza
    0.43
     hansen
    0.43
    didReceive
    0.43
    sieur
    0.42
     proprietary
    0.42
    ៗ
    0.41
     marketing
    0.41
    isseaux
    0.41
    Activations Density 0.123%

    No Known Activations