© 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. 1076
    Prev
    Next
    INDEX
    Explanations

    references to social dynamics and competition among individuals

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

    Attractive people or beauty

    np_acts-logits-general · gemini-2.0-flash

    physical attractiveness

    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
    ThroughAttribute
    -0.73
    SOUNDBITE
    -0.68
    titleMargin
    -0.64
     expéri
    -0.63
     propOrder
    -0.63
    gestone
    -0.61
    HttpPut
    -0.59
    raded
    -0.59
    évaluateur
    -0.58
     nawr
    -0.58
    POSITIVE LOGITS
     handsome
    1.24
     attractive
    1.11
    handsome
    1.06
     sexy
    1.03
     beauty
    1.00
    attractive
    0.99
     attractiveness
    0.99
     Handsome
    0.94
     beautiful
    0.94
    Handsome
    0.91
    Activations Density 0.205%

    No Known Activations