© 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. 22-GEMMASCOPE-RES-16K
    11. 5062
    Prev
    Next
    INDEX
    Explanations

    elements related to color description and visual details in artistic contexts

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

    Colors, especially shades and tones

    np_acts-logits-general · gemini-2.0-flash

    color shades and tones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     white
    -0.75
     black
    -0.67
    white
    -0.64
     weißen
    -0.63
     White
    -0.62
     bianchi
    -0.61
    White
    -0.60
     siyah
    -0.59
     WHITE
    -0.58
     białe
    -0.56
    POSITIVE LOGITS
     shades
    0.80
     tone
    0.80
     tones
    0.80
     виправивши
    0.77
     ostavi
    0.77
     tinge
    0.77
     shade
    0.76
     darkening
    0.75
     deepening
    0.74
     shading
    0.73
    Activations Density 0.137%

    No Known Activations