© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 461
    Prev
    Next
    INDEX
    Explanations

    key political figures and their influence within legislative contexts

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

    Political figures and related terms

    np_acts-logits-general · gemini-2.0-flash

    elected officials and legislators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    ThroughAttribute
    -0.47
     Picchu
    -0.38
    transient
    -0.35
    figuration
    -0.35
     realization
    -0.34
    RTRS
    -0.33
     toques
    -0.33
    chymal
    -0.32
     company
    -0.32
     realisation
    -0.32
    POSITIVE LOGITS
     legislator
    0.70
    KommentareTeilen
    0.69
     congressman
    0.65
     Congressman
    0.62
     legislators
    0.62
     lawmaker
    0.60
     senator
    0.59
    HomeAsUpEnabled
    0.58
    Senator
    0.58
     Legisl
    0.58
    Activations Density 0.156%

    No Known Activations