Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11577
    Prev
    Next
    INDEX
    Explanations

    HTML structure and elements within a webpage

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

    HTML list elements (li, ul) and code

    np_acts-logits-general · gemini-2.0-flash

    HTML, code, and math notation

    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
    حياتها
    -0.68
    NewUrlParser
    -0.62
    CreateMap
    -0.62
    mergeFrom
    -0.62
     autorytatywna
    -0.59
     ویکی‌پدیا
    -0.58
     Paglinawan
    -0.58
     وتسجيلات
    -0.58
     صوتيه
    -0.56
    KommentareTeilen
    -0.56
    POSITIVE LOGITS
    ↵
    0.53
    thinkable
    0.52
    //});
    0.51
    chaun
    0.47
     addSubview
    0.47
    </table>
    0.46
    Personensuche
    0.46
    setViewportView
    0.46
    arschu
    0.46
    qrt
    0.45
    Activations Density 0.056%

    No Known Activations