© 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. 3-GEMMASCOPE-RES-16K
    11. 7921
    Prev
    Next
    INDEX
    Explanations

    references to killing and murder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iNdEx
    -0.76
     متحده
    -0.76
     Himo
    -0.73
     >",
    -0.72
     wireType
    -0.68
    theless
    -0.67
    อิง
    -0.65
    cheme
    -0.64
     Manus
    -0.64
    arabe
    -0.63
    POSITIVE LOGITS
     kill
    3.04
     kills
    2.83
     killing
    2.73
     Kill
    2.71
     KILL
    2.68
    kill
    2.68
     killed
    2.67
    Kill
    2.50
     Kills
    2.40
    KILL
    2.35
    Activations Density 0.053%

    No Known Activations