© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9960
    Prev
    Next
    INDEX
    Explanations

    special annotations or metadata in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.73
    addCriterion
    -0.69
    tvguidetime
    -0.69
    XmlAccessorType
    -0.67
     ../../
    -0.66
     المعيارى
    -0.63
    ContentLoaded
    -0.62
     Abonnez
    -0.62
     hạ
    -0.61
     poffible
    -0.60
    POSITIVE LOGITS
     ord
    0.67
     attached
    0.63
     spread
    0.61
     Alb
    0.57
     unpaid
    0.55
    Scrolled
    0.55
     reserved
    0.55
     ocean
    0.54
     ordained
    0.54
    ord
    0.52
    Activations Density 0.034%

    No Known Activations