© 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. 20-GEMMASCOPE-RES-16K
    11. 8414
    Prev
    Next
    INDEX
    Explanations

    mentions of political roles and positions

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

    Preceding tokens before a mathematical or legal reference

    np_acts-logits-general · gemini-2.0-flash

    Caribbean countries and official government documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Puget
    -0.73
     canceled
    -0.69
     coö
    -0.69
     theaters
    -0.68
     flavors
    -0.67
     Spokane
    -0.64
     NLRB
    -0.63
     neighbors
    -0.63
     Moby
    -0.63
    canceled
    -0.62
    POSITIVE LOGITS
     Guyana
    0.89
     Jamaica
    0.88
     Barbados
    0.85
    Kaieteur
    0.81
    Guyana
    0.78
     artiste
    0.78
    Barbados
    0.78
     Tobago
    0.78
    Jamaica
    0.76
     Caribbean
    0.74
    Activations Density 0.087%

    No Known Activations