© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 110732
    Prev
    Next
    INDEX
    Explanations

    details about physical appearance and characteristics

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

    physical descriptions and beauty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     masculinos
    -0.55
     masculinity
    -0.54
     lelaki
    -0.54
     męski
    -0.53
     masculina
    -0.52
     männ
    -0.50
    Beard
    -0.50
     manhood
    -0.50
     gruesa
    -0.50
    bearded
    -0.50
    POSITIVE LOGITS
     beauty
    0.94
     beautiful
    0.87
    beauty
    0.75
     prettiest
    0.75
    beautiful
    0.74
     Beauty
    0.73
     Beautiful
    0.72
     prettier
    0.68
     gorgeous
    0.67
     cantik
    0.66
    Activations Density 0.099%

    No Known Activations