© 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. 4-GEMMASCOPE-RES-16K
    11. 10524
    Prev
    Next
    INDEX
    Explanations

    instances of values or scores related to medication and therapy outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -1.04
    Tikang
    -0.90
    bootstrapcdn
    -0.88
     pinulongan
    -0.86
    Referencies
    -0.82
    NUMX
    -0.82
    elry
    -0.80
     lenker
    -0.73
     BoxDecoration
    -0.73
     تضيفلها
    -0.72
    POSITIVE LOGITS
    *
    1.30
     *
    0.90
    //
    0.87
    ())),
    0.86
    *),
    0.83
    <eos>
    0.79
    //
    0.78
     •
    0.77
    *)
    0.77
    *,
    0.76
    Activations Density 0.066%

    No Known Activations