© 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. 10772
    Prev
    Next
    INDEX
    Explanations

    references to political campaigns and candidate strategies

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

    Presidential campaigns and debates

    np_acts-logits-general · gemini-2.0-flash

    presidential debates and campaigns

    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
    PHONY
    -0.62
    DispatchToProps
    -0.58
    namentales
    -0.56
     disambiguazione
    -0.56
    Abp
    -0.55
    ⓧ
    -0.54
    +};
    -0.53
    StructEnd
    -0.52
    qrstuvwxyz
    -0.51
    codegen
    -0.49
    POSITIVE LOGITS
     debate
    1.01
     debates
    0.91
    debate
    0.83
     Debate
    0.80
     Debates
    0.77
    Debate
    0.76
     primary
    0.76
    primary
    0.70
     DEB
    0.70
     debated
    0.70
    Activations Density 0.264%

    No Known Activations