© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13628
    Prev
    Next
    INDEX
    Explanations

    references to political roles and events

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

    preceding titles like "Prime Minister" or "president."

    np_acts-logits-general · gemini-2.0-flash

    president or prime minister

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.59
    UnusedPrivate
    -0.54
     Partagez
    -0.51
     Staff
    -0.51
    teil
    -0.51
    ocities
    -0.50
    toHaveBeenCalled
    -0.49
    teilen
    -0.49
    anglès
    -0.47
     STAFF
    -0.47
    POSITIVE LOGITS
     president
    1.59
     President
    1.38
    president
    1.30
    President
    1.25
     leader
    1.14
     PRESIDENT
    1.09
     boss
    1.04
     presidente
    1.03
     governor
    1.02
    PRESIDENT
    1.00
    Activations Density 0.282%

    No Known Activations