© 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. 20-GEMMASCOPE-RES-16K
    11. 3528
    Prev
    Next
    INDEX
    Explanations

    references to medical and biological contexts, including patients, organs, and anatomical structures

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

    preceding plural nouns

    np_acts-logits-general · gemini-2.0-flash

    places, objects, and biological entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     engagement
    -0.69
     arrangements
    -0.69
     scenarios
    -0.67
     impressions
    -0.66
     trials
    -0.66
     engagements
    -0.66
     Reſ
    -0.66
     expressions
    -0.65
     assessments
    -0.65
     actions
    -0.65
    POSITIVE LOGITS
     prisonniers
    0.74
     blessés
    0.70
     marquées
    0.70
     peggio
    0.68
     chrétiens
    0.66
     dieux
    0.65
     réfugiés
    0.65
     prêtres
    0.65
     africains
    0.64
     élas
    0.63
    Activations Density 0.980%

    No Known Activations