© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1120
    Prev
    Next
    INDEX
    Explanations

    terms related to injury or casualty in the context of conflict or violence

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

    "wounded" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    wounded or shot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iastes
    -0.52
     للاسماء
    -0.47
    ніципалі
    -0.45
     betweenstory
    -0.45
    NSUserDefaults
    -0.43
     Krzysztof
    -0.43
     الرخصة
    -0.43
    verwijspagina
    -0.42
     Period
    -0.40
    cloudfront
    -0.40
    POSITIVE LOGITS
     wounded
    0.87
     heridas
    0.82
     wounds
    0.81
     herida
    0.79
     heridos
    0.77
     herido
    0.72
     injured
    0.68
     Wounds
    0.68
     Wounded
    0.65
     wounding
    0.65
    Activations Density 0.304%

    No Known Activations