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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15086
    Prev
    Next
    INDEX
    Explanations

    discussions and statements about accountability and legislative actions.

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

    statistical or legislative information such as numbers, names, and political terms.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    This neuron appears to be detecting mentions of U.S. Representatives and Senators, particularly Republicans. It shows high activation for patterns like: "Rep. [Name] (R-[State])" "Sen. [Name] (R-[State])" It

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    "Rep" or "Representative" followed by a name

    np_acts-logits-general · gemini-2.0-flash

    Representative followed by names

    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
    ArrowToggle
    -0.65
    hObject
    -0.61
    xnn
    -0.59
     linkovi
    -0.57
    enumii
    -0.57
    حياته
    -0.57
    ":[{
    -0.56
     الرياضيه
    -0.56
    DeleteBehavior
    -0.55
    nonatomic
    -0.55
    POSITIVE LOGITS
     Rep
    0.95
    Reps
    0.86
    Rep
    0.86
     Reps
    0.80
    Representative
    0.72
     Representative
    0.72
     rep
    0.69
     REP
    0.66
    rep
    0.62
     REPRESENT
    0.62
    Activations Density 0.136%

    No Known Activations