© 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. 8553
    Prev
    Next
    INDEX
    Explanations

    references to basketball players and their achievements.

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

    words related to NBA basketball and basketball players.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of top athletes or sports figures, particularly in comparative or ranking contexts. It seems to activate strongly for phrases that discuss the greatest or highest-ranked players in a sport, especially basketball and football, as well as when comparing players or teams against each other.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Follows a number indicating a ranking

    np_acts-logits-general · gemini-2.0-flash

    greatest players

    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
    帖最后由
    -0.65
    Hochspringen
    -0.63
    )_/¯
    -0.61
    Korn
    -0.58
    utiva
    -0.56
     estekak
    -0.55
    ReusableCell
    -0.54
    structors
    -0.54
    virons
    -0.54
     DRAWINGS
    -0.53
    POSITIVE LOGITS
     GOAT
    0.75
     superstar
    0.64
     Messi
    0.64
     superstars
    0.64
     supreme
    0.62
     dominance
    0.61
    🐐
    0.60
    GOAT
    0.60
    Messi
    0.58
     invincible
    0.58
    Activations Density 0.218%

    No Known Activations