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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9433
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols used in coding syntax

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

    Code, markup, and file format tags

    np_acts-logits-general · gemini-2.0-flash

    signals or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    новниш
    -0.69
    хьтан
    -0.67
     noDo
    -0.61
    Попис
    -0.61
    InitVars
    -0.60
    енча
    -0.58
    SharedDtor
    -0.58
    AddHtmlAttribute
    -0.57
     فريبيس
    -0.56
    kháu
    -0.55
    POSITIVE LOGITS
     تضيفلها
    0.58
    허
    0.56
     وتسجيلات
    0.52
    เป็น
    0.50
    ipient
    0.49
     Must
    0.48
    ärzt
    0.47
    hetta
    0.47
    oté
    0.47
     must
    0.47
    Activations Density 0.056%

    No Known Activations