© 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 - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3664
    Prev
    Next
    INDEX
    Explanations

    references to civilian casualties and violence in conflict scenarios

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

    deaths, casualties, or injuries

    np_acts-logits-general · gemini-2.0-flash

    deaths and casualties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.82
     للمعارف
    -0.78
    SPATH
    -0.69
    "]();
    -0.62
    isEmail
    -0.62
     kaarangay
    -0.62
    @[+][
    -0.61
     ostavi
    -0.60
     esternos
    -0.60
     tartalomajánló
    -0.59
    POSITIVE LOGITS
     killed
    0.85
     casualties
    0.84
     fatalities
    0.78
     injured
    0.76
     died
    0.71
     innocent
    0.71
     deaths
    0.70
     Casual
    0.69
     Killed
    0.67
     dead
    0.67
    Activations Density 0.184%

    No Known Activations