© 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. 8932
    Prev
    Next
    INDEX
    Explanations

    references to political topics and entities

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

    Following "political" or discussing "politics"

    np_acts-logits-general · gemini-2.0-flash

    political career, opinions, agenda, party, donations, office

    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
    makeConstraints
    -0.63
     cref
    -0.56
    ➟
    -0.53
     NDL
    -0.52
    EndInit
    -0.52
     protoimpl
    -0.51
    elemField
    -0.50
    enderror
    -0.49
    Tikang
    -0.49
    цездатний
    -0.49
    POSITIVE LOGITS
     politics
    0.98
     POLITICS
    0.91
    politics
    0.90
     Politics
    0.85
    Politics
    0.83
     POLITICAL
    0.81
    political
    0.81
     political
    0.81
    Political
    0.76
     politician
    0.76
    Activations Density 0.124%

    No Known Activations