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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 400
    Prev
    Next
    INDEX
    Explanations

    specific scientific terminology and classifications related to research studies

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

    scientific or technical terminology related to research and data analysis.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    IVEREF
    -0.49
     getArguments
    -0.45
    principalTable
    -0.44
    MigrationBuilder
    -0.42
    SuspendLayout
    -0.42
    warf
    -0.42
    ValueStyle
    -0.41
    Portail
    -0.41
    (!__
    -0.40
     ExecuteAsync
    -0.39
    POSITIVE LOGITS
    WebElementEntity
    0.46
     للاسماء
    0.45
     चीज़ों
    0.42
     Nusantara
    0.40
     وتسجيلات
    0.40
    alogie
    0.38
     esat
    0.38
    mitives
    0.37
     gyhoeddwyd
    0.36
    出版年
    0.36
    Activations Density 0.485%

    No Known Activations