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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 988
    Prev
    Next
    INDEX
    Explanations

    information related to roofing products and their characteristics

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

    descriptions of roofing material characteristics and specifications

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

    (this);

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     makeshift
    -0.61
    новниш
    -0.60
     ThemeData
    -0.60
    BuildContext
    -0.56
    homemade
    -0.56
     homemade
    -0.55
    MigrationBuilder
    -0.55
    WindowConstants
    -0.55
     препратки
    -0.54
    nestjs
    -0.53
    POSITIVE LOGITS
    otechnology
    0.60
    Становништво
    0.59
    Hentet
    0.58
    bootstrapcdn
    0.52
    msgTypes
    0.52
     invokingState
    0.51
    EClass
    0.51
    modelBuilder
    0.50
     portfolio
    0.50
     composizione
    0.49
    Activations Density 0.034%

    No Known Activations