© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 875
    Prev
    Next
    INDEX
    Explanations

    elements related to elegance and sophistication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bière
    -0.62
     camisetas
    -0.62
     Australie
    -0.58
     camiseta
    -0.55
     vélo
    -0.54
     campamento
    -0.54
    isième
    -0.53
     colère
    -0.52
     birra
    -0.52
    вик
    -0.52
    POSITIVE LOGITS
     elegance
    1.03
     elegant
    1.01
     Elegant
    0.97
    Elegant
    0.95
     elegan
    0.87
     Cocktail
    0.85
    elegante
    0.85
     Elegance
    0.84
     elegantly
    0.84
    cocktail
    0.83
    Activations Density 0.379%

    No Known Activations