© 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. 1133
    Prev
    Next
    INDEX
    Explanations

    references to talent and achievement, particularly in the context of individual success and hard work

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

    talent or discovering talent

    np_acts-logits-general · gemini-2.0-flash

    talent and potential

    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
    migrationBuilder
    -0.68
    twimg
    -0.67
    addCriterion
    -0.61
     PARSER
    -0.60
     snippetHide
    -0.59
    StoreMessageInfo
    -0.58
    CloseOperation
    -0.57
    DockStyle
    -0.56
    keyColumn
    -0.56
    +#+#
    -0.56
    POSITIVE LOGITS
     talent
    2.31
     talents
    2.03
     Talent
    1.85
    talent
    1.84
    Talent
    1.70
     talento
    1.69
     Talents
    1.64
     talented
    1.63
     talentos
    1.58
     талан
    1.49
    Activations Density 0.204%

    No Known Activations