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-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1176
    Prev
    Next
    INDEX
    Explanations

    color-related property definitions in code

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

    color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     مشين
    -0.75
    دانشنامهٔ
    -0.72
    RenderAtEndOf
    -0.69
    WaitGroup
    -0.68
    reportWebVitals
    -0.68
     <<<<<<<<<<<<<<
    -0.65
    AddTagHelper
    -0.63
     незавершена
    -0.61
     فريبيس
    -0.61
    ">//
    -0.57
    POSITIVE LOGITS
     color
    1.08
     colors
    0.99
    color
    0.96
     colour
    0.96
    Color
    0.93
     Color
    0.90
     colours
    0.88
    colors
    0.85
     colores
    0.85
     COLOR
    0.81
    Activations Density 0.038%

    No Known Activations