© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27435
    Prev
    Next
    INDEX
    Explanations

    terms related to aggression in behavior

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

    aggressive behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.67
    وت
    -0.58
    ::<
    -0.57
     WONDER
    -0.57
     pés
    -0.56
    {~
    -0.56
    зан
    -0.55
    hoga
    -0.54
     Fonseca
    -0.54
    وج
    -0.54
    POSITIVE LOGITS
     aggres
    1.19
     aggressiveness
    1.08
     Aggression
    1.08
     myſelf
    1.07
     agres
    1.03
     Monfieur
    0.98
     itſelf
    0.97
     aggression
    0.93
     Agre
    0.91
    ConstraintMaker
    0.90
    Activations Density 0.013%

    No Known Activations