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. 9336
    Prev
    Next
    INDEX
    Explanations

    cultural references and descriptors across various subjects

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

    "across", "by", or "among" preceding a category

    np_acts-logits-general · gemini-2.0-flash

    across categories and groups

    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
     onCreateView
    -0.83
    HtmlAttribute
    -0.60
    rawDesc
    -0.56
     Offisielt
    -0.48
    lijkse
    -0.47
     onBind
    -0.46
    BeginContext
    -0.46
    atrième
    -0.46
    ungguhnya
    -0.46
    softc
    -0.43
    POSITIVE LOGITS
     types
    1.52
     species
    1.46
     genres
    1.43
     genre
    1.38
     categories
    1.32
     type
    1.28
     styles
    1.23
     TYPES
    1.21
     formats
    1.19
    types
    1.16
    Activations Density 1.771%

    No Known Activations