© 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. 18-GEMMASCOPE-RES-16K
    11. 938
    Prev
    Next
    INDEX
    Explanations

    references to color and variations of the word 'color'

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

    "color" or related terms

    np_acts-logits-general · gemini-2.0-flash

    colorable showing of factual innocence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.97
    makeConstraints
    -0.87
    BibitemShut
    -0.82
    yntaxException
    -0.81
     themſelves
    -0.81
    }*/
    -0.80
     <=",
    -0.80
    soever
    -0.79
    };*/
    -0.77
    Jereo
    -0.77
    POSITIVE LOGITS
     color
    0.75
     getColor
    0.73
    色的
    0.73
     Color
    0.72
     COLOR
    0.71
    SetColor
    0.69
     colores
    0.68
     colors
    0.67
    COLOR
    0.66
    colors
    0.65
    Activations Density 0.061%

    No Known Activations