© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 7804
    Prev
    Next
    INDEX
    Explanations

    terms related to violence and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.50
    Dorm
    -0.47
    })));
    -0.46
     audition
    -0.45
     распро
    -0.45
     seny
    -0.45
     Sweep
    -0.45
     Verhältnisse
    -0.45
     Bette
    -0.45
    rté
    -0.44
    POSITIVE LOGITS
     violent
    0.77
     Violent
    0.70
     bitter
    0.65
     violence
    0.65
     blunt
    0.64
     violento
    0.63
     bl
    0.63
     violenta
    0.63
    violent
    0.62
     violently
    0.61
    Activations Density 0.339%

    No Known Activations