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. 10744
    Prev
    Next
    INDEX
    Explanations

    structured data and control flow elements in programming contexts

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

    Code snippets and file paths

    np_acts-logits-general · gemini-2.0-flash

    code comments and mathematical symbols

    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
    例文帳に追加
    -0.73
    stdafx
    -0.71
     typelib
    -0.68
    CppMethod
    -0.66
    InjectAttribute
    -0.64
    styleUrls
    -0.62
    IsContent
    -0.61
    Lähteet
    -0.59
     disambiguazione
    -0.57
    قایناقلار
    -0.57
    POSITIVE LOGITS
    enderror
    0.81
    AnchorTagHelper
    0.70
    KommentareTeilen
    0.69
     Offisielt
    0.69
     pleaſure
    0.65
     بيها
    0.62
    何より
    0.62
     myſelf
    0.62
     Anyways
    0.61
    Поэтому
    0.60
    Activations Density 0.717%

    No Known Activations