© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 7626
    Prev
    Next
    INDEX
    Explanations

    references to polymers and their attributes

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

    Follows the tokens "poly", "pl", "curs", "amet", or "micro"

    np_acts-logits-general · gemini-2.0-flash

    polymers, plurals OR cursors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lèvres
    -0.98
     vérit
    -0.94
     leçons
    -0.88
     épaules
    -0.86
     renseignements
    -0.80
     négociations
    -0.80
     bienfaits
    -0.80
     églises
    -0.79
     gouvernements
    -0.78
     boî
    -0.77
    POSITIVE LOGITS
     gases
    0.72
     soils
    0.71
     steels
    0.71
     gardens
    0.70
     furs
    0.69
    woods
    0.68
     beers
    0.67
     colors
    0.67
    boards
    0.66
     mails
    0.65
    Activations Density 0.180%

    No Known Activations