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. 13852
    Prev
    Next
    INDEX
    Explanations

    references to a specific operating system and its components

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

    the "os" library or module

    np_acts-logits-general · gemini-2.0-flash

    os followed by hyphen or other specific tokens

    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
    IsContent
    -0.68
    EqualsAnd
    -0.61
    Tikang
    -0.60
    Jeografia
    -0.59
    VersionUID
    -0.59
    mrc
    -0.58
     Jurí
    -0.54
    CreateMap
    -0.51
    entration
    -0.50
    cuits
    -0.49
    POSITIVE LOGITS
     Os
    0.90
    ValueStyle
    0.78
    Os
    0.72
     للاسماء
    0.71
     os
    0.64
     فريبيس
    0.64
     OS
    0.58
    ServiceModel
    0.57
     OST
    0.56
    getRuntime
    0.54
    Activations Density 0.075%

    No Known Activations