© 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 - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 8108
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of killing or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tfsi
    -0.96
    theless
    -0.93
    المناصب
    -0.91
     Portman
    -0.88
    mopolitan
    -0.85
     Himo
    -0.81
     varandra
    -0.79
     INTE
    -0.79
     placés
    -0.78
     Folks
    -0.77
    POSITIVE LOGITS
     Kill
    1.20
     KILL
    1.11
     kill
    1.05
     kills
    0.95
    kill
    0.95
    KILL
    0.91
    Kill
    0.89
     kil
    0.84
     Kil
    0.81
     TRIG
    0.79
    Activations Density 0.056%

    No Known Activations