© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14349
    Prev
    Next
    INDEX
    Explanations

    references to politicians and government officials

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

    mentions of specific high-profile public officials—especially politicians and heads of government—often alongside their formal titles.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    names of political leaders and heads of state, particularly when followed by verbs or possessive markers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     Jan
    -0.36
    enderror
    -0.35
     désolés
    -0.35
     ffilmiau
    -0.34
    ніципалі
    -0.34
    violet
    -0.34
    fdata
    -0.34
     variety
    -0.34
    ="../
    -0.33
     Ca
    -0.33
    POSITIVE LOGITS
    phosa
    0.97
    uterte
    0.73
     Obrador
    0.71
    sonaro
    0.66
     himſelf
    0.66
    anyahu
    0.62
     Bolsonaro
    0.62
     Jokowi
    0.60
     Widodo
    0.59
    ScopeManager
    0.58
    Activations Density 0.163%

    No Known Activations