© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4641
    Prev
    Next
    INDEX
    Explanations

    descriptions of colors, particularly shades of purple, pink, and other vivid colors in various contexts

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

    Colors, especially pink and purple

    np_acts-logits-general · gemini-2.0-flash

    purple and pink

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -1.02
    GEBURTSDATUM
    -0.86
     nahilalakip
    -0.81
    Personensuche
    -0.80
     estekak
    -0.76
    expandindo
    -0.74
    المناصب
    -0.70
     <=",
    -0.69
    
    -0.68
     ujednoznacz
    -0.68
    POSITIVE LOGITS
     color
    0.86
    ish
    0.78
     colour
    0.77
     hue
    0.77
     colored
    0.69
     hues
    0.69
    farben
    0.69
     coloration
    0.69
     tinge
    0.67
     tinged
    0.66
    Activations Density 0.151%

    No Known Activations