© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5786
    Prev
    Next
    INDEX
    Explanations

    government-related terms and references to emergency services and safety measures

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

    Titles or roles after organizations

    np_acts-logits-general · gemini-2.0-flash

    official roles and titles

    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
     akik
    -0.56
     umane
    -0.48
    gados
    -0.46
    "]').
    -0.45
     perifer
    -0.44
     chré
    -0.44
     timpul
    -0.44
    duğu
    -0.44
     monaster
    -0.43
     hendes
    -0.43
    POSITIVE LOGITS
     spokeswoman
    1.31
     Director
    1.27
     spokesman
    1.23
     Chief
    1.18
     President
    1.17
     Chairman
    1.16
     director
    1.16
     founder
    1.16
     CEO
    1.15
     historian
    1.15
    Activations Density 0.252%

    No Known Activations