© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 681
    Prev
    Next
    INDEX
    Explanations

    references to government or organizational officials

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

    terms related to government or authoritative entities

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

    government officials' actions

    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
    enumi
    -0.67
    es
    -0.64
     estekak
    -0.63
    oflavin
    -0.59
    іга
    -0.57
    reciate
    -0.56
    webElementXpaths
    -0.55
    +:+
    -0.55
     Nus
    -0.55
     mergeFrom
    -0.54
    POSITIVE LOGITS
     responsible
    0.79
     officials
    0.77
     GIPHY
    0.71
    ')));
    0.69
    ials
    0.67
     Officials
    0.65
    ))));
    0.64
    Officials
    0.63
    IALS
    0.62
     involved
    0.61
    Activations Density 0.029%

    No Known Activations