© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9261
    Prev
    Next
    INDEX
    Explanations

    terms related to violence and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gub
    -0.49
     Lazy
    -0.47
     lazy
    -0.47
     sou
    -0.46
    懒
    -0.42
    elm
    -0.41
    Lazy
    -0.41
     cre
    -0.41
     small
    -0.40
     top
    -0.40
    POSITIVE LOGITS
     attack
    1.90
     violence
    1.84
     attacks
    1.79
     massacre
    1.77
     assault
    1.75
    Violence
    1.65
     assaults
    1.65
     Attacks
    1.65
     violent
    1.61
     massacres
    1.60
    Activations Density 3.363%

    No Known Activations