© 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. 23-GEMMASCOPE-RES-16K
    11. 15652
    Prev
    Next
    INDEX
    Explanations

    references to incidents of violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Iber
    -0.50
     Guadeloupe
    -0.49
     Tenerife
    -0.49
     Llu
    -0.48
     Cayman
    -0.48
     Baruch
    -0.48
     Mallorca
    -0.47
     isle
    -0.47
     Braz
    -0.47
    CGContext
    -0.47
    POSITIVE LOGITS
     Afghan
    1.57
     Afghanistan
    1.56
     Kabul
    1.56
     Taliban
    1.47
     Afghans
    1.37
    Afghanistan
    1.36
     afghan
    1.31
    Afghan
    1.31
     Afgan
    1.16
     Kand
    1.02
    Activations Density 0.074%

    No Known Activations