Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 16167
    Prev
    Next
    INDEX
    Explanations

    words that describe beauty or positive aesthetic qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.94
    msgSender
    -0.85
    eraard
    -0.82
     aggressiveness
    -0.80
    AndEndTag
    -0.80
     SqlCommand
    -0.80
    setVerticalGroup
    -0.79
    IsContent
    -0.79
     MainAxisSize
    -0.79
     Anfitrión
    -0.77
    POSITIVE LOGITS
     beautiful
    2.12
    Beautiful
    1.96
     Beautiful
    1.93
    beautiful
    1.92
     BEAUTIFUL
    1.78
     gorgeous
    1.64
    BEAUT
    1.47
     lovely
    1.44
     beautifully
    1.37
     pięk
    1.37
    Activations Density 0.038%

    No Known Activations