© 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. 21-GEMMASCOPE-RES-16K
    11. 6337
    Prev
    Next
    INDEX
    Explanations

    historical references related to specific individuals and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     penicillin
    -0.52
     Yugoslavia
    -0.50
     airst
    -0.49
     radio
    -0.49
     Radio
    -0.48
     RADIO
    -0.47
    fiées
    -0.46
     Référence
    -0.46
     postwar
    -0.46
     comunista
    -0.45
    POSITIVE LOGITS
    日閲覧
    0.89
    SequentialGroup
    0.80
     Victorian
    0.70
     Crimean
    0.67
     crin
    0.64
    Hauptartikel
    0.63
    Datuak
    0.63
    الحياه
    0.62
    endphp
    0.61
    Victorian
    0.60
    Activations Density 0.414%

    No Known Activations