© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10606
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and injuries

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

    injuries

    np_acts-logits-general · gemini-2.0-flash

    injury from broken bones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.79
    UnusedPrivate
    -0.63
    makeConstraints
    -0.56
    webElementXpaths
    -0.53
    ResponseWriter
    -0.53
    UserScript
    -0.52
     HasFactory
    -0.47
     autorytatywna
    -0.46
    UseVisualStyle
    -0.45
     препратки
    -0.45
    POSITIVE LOGITS
     injury
    1.46
     injured
    1.39
     injuries
    1.34
     Injury
    1.29
     Injured
    1.20
    Injury
    1.20
    injury
    1.16
     Injuries
    1.13
    Injuries
    1.12
     injure
    1.11
    Activations Density 0.205%

    No Known Activations