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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15882
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and programming structures

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

    Mathematical expressions and code snippets

    np_acts-logits-general · gemini-2.0-flash

    assuming conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.47
    Hentet
    -0.47
     ddelweddau
    -0.42
    География
    -0.40
    УДК
    -0.38
    ⇑
    -0.38
     AssemblyTitle
    -0.38
    KommentareTeilen
    -0.37
     lẻ
    -0.36
    forName
    -0.35
    POSITIVE LOGITS
     kaarangay
    0.55
    rungsseite
    0.54
    tagHelperRunner
    0.53
     Италијани
    0.51
     fieldNum
    0.51
     Мексичка
    0.50
    IntoConstraints
    0.49
    AddTagHelper
    0.48
     μεγ
    0.47
     isNameExpr
    0.46
    Activations Density 2.419%

    No Known Activations