© 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. 20-GEMMASCOPE-RES-16K
    11. 8836
    Prev
    Next
    INDEX
    Explanations

    themes related to opportunities and abilities, particularly in the context of decisions and choices

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

    Preceding words of infinitive "to"

    np_acts-logits-general · gemini-2.0-flash

    opportunity to do

    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
    iprot
    -0.76
    исленность
    -0.68
     ExecuteAsync
    -0.65
    PerformLayout
    -0.64
    endregion
    -0.64
     surla
    -0.59
     insuffisamment
    -0.58
    dibles
    -0.57
    parseFrom
    -0.56
     restTemplate
    -0.56
    POSITIVE LOGITS
     to
    1.59
     чтобы
    0.96
     để
    0.81
     щоб
    0.77
     upang
    0.75
     לעשות
    0.72
     untuk
    0.68
     להשת
    0.68
    ในการ
    0.65
    Чтобы
    0.65
    Activations Density 0.696%

    No Known Activations