© 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. 1086
    Prev
    Next
    INDEX
    Explanations

    variations of the word "pretty."

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

    Comes before adjectives like "soon", "small", "difficult", "clear"

    np_acts-logits-general · gemini-2.0-flash

    pretty + descriptive word

    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
     alluminio
    -0.58
     NgModule
    -0.56
    <h1>
    -0.54
    ToBounds
    -0.53
     transférez
    -0.53
     Autorizaciones
    -0.53
    hire
    -0.52
     vuitton
    -0.52
    🎰
    -0.52
    ToOne
    -0.51
    POSITIVE LOGITS
     darn
    1.20
     pretty
    0.94
     damn
    0.91
    pretty
    0.85
     Pretty
    0.82
    Pretty
    0.81
     PRET
    0.78
    damn
    0.74
     much
    0.74
     damned
    0.73
    Activations Density 0.046%

    No Known Activations