© 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. 8-GEMMASCOPE-RES-16K
    11. 6212
    Prev
    Next
    INDEX
    Explanations

    references to heaviness or significant weight in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.02
    Hochspringen
    -0.88
     незавершена
    -0.70
    momile
    -0.70
     trustees
    -0.69
    QName
    -0.69
     QName
    -0.69
    :✨
    -0.67
     hâte
    -0.67
    PMailer
    -0.66
    POSITIVE LOGITS
     heavy
    1.58
     Heavy
    1.54
    Heavy
    1.54
    heavy
    1.50
     HEAVY
    1.45
     heaviest
    1.29
     Heav
    1.14
     heavier
    1.13
    heav
    1.12
     Schwer
    1.09
    Activations Density 0.056%

    No Known Activations