© 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. 19-GEMMASCOPE-RES-16K
    11. 3475
    Prev
    Next
    INDEX
    Explanations

    intense emotional or physical violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.80
    providedIn
    -0.79
     kasarigan
    -0.78
     ModelExpression
    -0.77
     Walkover
    -0.76
     AssemblyProduct
    -0.76
     surla
    -0.75
    GIH
    -0.73
    UnusedPrivate
    -0.72
     Вікі
    -0.71
    POSITIVE LOGITS
     ripping
    0.79
     rip
    0.77
     torn
    0.77
     ripped
    0.74
     tore
    0.70
     tearing
    0.69
     tear
    0.68
    split
    0.67
     split
    0.67
     sever
    0.66
    Activations Density 0.181%

    No Known Activations