© 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. 7876
    Prev
    Next
    INDEX
    Explanations

    elements related to ratings and classifications

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

    similarity or continuation

    np_acts-logits-general · gemini-2.0-flash

    similarity or another

    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
    RectangleBorder
    -0.68
     totiž
    -0.61
     derfor
    -0.61
     namelijk
    -0.60
     anyway
    -0.58
    endphp
    -0.57
    それが
    -0.55
    annique
    -0.55
    #![
    -0.54
    Ведь
    -0.52
    POSITIVE LOGITS
     ebenfalls
    2.04
     similarly
    1.78
    another
    1.75
     another
    1.74
    Another
    1.64
     szint
    1.61
    こちらも
    1.61
    ditto
    1.58
     Another
    1.55
     likewise
    1.54
    Activations Density 0.978%

    No Known Activations