© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9814
    Prev
    Next
    INDEX
    Explanations

    references to prisoners of war and their treatment during conflicts

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

    Prisoners of war and hostage situations

    np_acts-logits-general · gemini-2.0-flash

    POWs and hostages

    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
     AssemblyCulture
    -0.40
    isRequired
    -0.37
    ResponseWriter
    -0.37
     defaultstate
    -0.35
     quartiere
    -0.35
     שוליים
    -0.35
    帖最后由
    -0.35
    makeConstraints
    -0.33
    ᅠ
    -0.33
     fijar
    -0.32
    POSITIVE LOGITS
     hostage
    0.83
     hostages
    0.83
     captives
    0.78
     captivity
    0.73
     captive
    0.72
     kidnapped
    0.71
     prisoners
    0.69
     prisoner
    0.68
     Prisoner
    0.67
     kidnap
    0.66
    Activations Density 0.450%

    No Known Activations