© 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. 2-GEMMASCOPE-RES-16K
    11. 3122
    Prev
    Next
    INDEX
    Explanations

    references to violent actions or incidents involving guns, shootings, and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calendriers
    -0.57
     समीक्षक
    -0.53
    verwijspagina
    -0.45
    long
    -0.43
    lieri
    -0.42
    kegaard
    -0.41
     long
    -0.41
    צב
    -0.41
    FAR
    -0.40
    ldr
    -0.40
    POSITIVE LOGITS
     punches
    0.80
     punching
    0.74
     punched
    0.73
     fainted
    0.70
     Punch
    0.69
     expulsion
    0.69
    juries
    0.67
     punch
    0.66
     kisses
    0.65
     PUNCH
    0.65
    Activations Density 0.804%

    No Known Activations