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. 21-GEMMASCOPE-RES-16K
    6. 7186
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in chess problem composition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.32
     occaf
    -0.30
     quæ
    -0.29
     defire
    -0.29
     theſe
    -0.29
     himſelf
    -0.29
    chaffenheit
    -0.29
     itſelf
    -0.28
     pleaſure
    -0.28
     people
    -0.28
    POSITIVE LOGITS
     ویکی‌پدی
    0.78
     Meksiku
    0.62
    avadoc
    0.62
     @"/
    0.59
     autorytatywna
    0.58
    DeleteBehavior
    0.57
    LEncoder
    0.56
     pinulongan
    0.55
    writeHead
    0.54
    attutto
    0.53
    Activations Density 1.985%

    No Known Activations