© 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. 21-GEMMASCOPE-RES-16K
    11. 3338
    Prev
    Next
    INDEX
    Explanations

    references to bodily injuries and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()]);
    -0.54
     Widerstand
    -0.48
    Soto
    -0.45
     kece
    -0.45
    phrine
    -0.44
    safe
    -0.43
    gesetzt
    -0.43
    gesterone
    -0.42
     yawn
    -0.42
     veneta
    -0.42
    POSITIVE LOGITS
     disability
    1.20
     disabilities
    1.17
     disabled
    1.13
     handicap
    1.12
     blindness
    1.10
     disable
    1.06
     Disability
    1.03
     permanently
    1.01
     handicapped
    1.01
     handicaps
    1.00
    Activations Density 0.405%

    No Known Activations