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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 35371
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and syntax related to imports and module handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    )_/¯
    -0.42
    จบ
    -0.41
     rodillas
    -0.40
     inesperado
    -0.40
     alcanzado
    -0.40
     alcance
    -0.40
     melay
    -0.39
     apropiado
    -0.39
    $_['
    -0.39
     poitrine
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.67
     utafitiHapana
    0.65
    Gweler
    0.45
     INTERESAR
    0.43
    poque
    0.42
    uric
    0.42
    ViewImports
    0.40
    Тарихы
    0.40
     Chwiliwch
    0.40
     pageContext
    0.40
    Activations Density 0.004%

    No Known Activations