© 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. 22-GEMMASCOPE-RES-16K
    11. 2392
    Prev
    Next
    INDEX
    Explanations

    specific mentions of dietary elements and their effects on health outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    that start with "Se" or "SE"

    np_acts-logits-general · gemini-2.0-flash

    sequestration, seeding, selenite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.75
     Liang
    -0.59
     Blanchard
    -0.57
    Liang
    -0.56
     Cry
    -0.54
     doInBackground
    -0.54
    دانشنامهٔ
    -0.54
     Flanagan
    -0.53
    DMETHOD
    -0.53
     Carlton
    -0.52
    POSITIVE LOGITS
     SE
    1.82
     Se
    1.72
    SE
    1.60
     Segal
    1.60
    Se
    1.59
     Sek
    1.56
     Се
    1.50
     Sé
    1.49
     Sean
    1.48
     SEC
    1.47
    Activations Density 0.366%

    No Known Activations