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. 14369
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and code structure

    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
    UrlResolution
    -0.68
     HasFactory
    -0.60
    IContainer
    -0.57
    onViewCreated
    -0.52
    providedIn
    -0.51
     ويكيپيديا
    -0.48
     ویکی‌پدیا
    -0.46
     تضيفلها
    -0.46
     kaynağından
    -0.46
    Demografie
    -0.45
    POSITIVE LOGITS
    Bust
    0.47
    annia
    0.44
    fisk
    0.44
     Verſ
    0.44
     bust
    0.44
    persky
    0.44
    realm
    0.43
     baz
    0.43
    fibre
    0.42
    puted
    0.42
    Activations Density 0.916%

    No Known Activations