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. 979
    Prev
    Next
    INDEX
    Explanations

    references to private entities or contexts

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

    terms related to private entities or organizations

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

    private companies, property, military

    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
    AndEndTag
    -0.75
    TypedDataSet
    -0.68
     Itself
    -0.67
    </thead>
    -0.65
     noqa
    -0.65
    GEBURTS
    -0.65
    (!__
    -0.63
    WriteTagHelper
    -0.63
     Италијани
    -0.63
    ✨:
    -0.63
    POSITIVE LOGITS
     sector
    0.66
    ::::::::::::::::
    0.58
    Private
    0.57
     cittadini
    0.57
    PRIVATE
    0.56
    er
    0.56
    Sector
    0.55
    कृत
    0.53
     Private
    0.53
     individuals
    0.50
    Activations Density 0.031%

    No Known Activations