© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 22482
    Prev
    Next
    INDEX
    Explanations

    terms related to fractures and injuries in a medical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arpur
    -0.54
    ostat
    -0.50
    onshire
    -0.48
    Assured
    -0.47
     bParam
    -0.47
    неопр
    -0.47
    setLayoutManager
    -0.46
    ToUse
    -0.46
    taan
    -0.46
    entan
    -0.46
    POSITIVE LOGITS
     injuries
    1.04
     Injuries
    1.02
     Injury
    0.99
     injury
    0.98
    Injury
    0.95
    injury
    0.90
     NSCoder
    0.86
     injure
    0.83
    Injuries
    0.81
    juries
    0.81
    Activations Density 0.062%

    No Known Activations