© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4041
    Prev
    Next
    INDEX
    Explanations

    references to color and its variations

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

    "color" or related concepts

    np_acts-logits-general · gemini-2.0-flash

    color development or coded

    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
    Personensuche
    -0.93
    BibitemShut
    -0.84
     <=",
    -0.83
    soever
    -0.81
    IndentedString
    -0.80
    makeConstraints
    -0.75
    Jereo
    -0.75
    )");
    
    -0.74
    SourceChecksum
    -0.73
    yntaxException
    -0.73
    POSITIVE LOGITS
     scheme
    0.77
     Scheme
    0.72
    coded
    0.72
     coded
    0.71
     coding
    0.66
     palette
    0.65
    色的
    0.64
    Scheme
    0.63
     getColor
    0.63
    blind
    0.60
    Activations Density 0.079%

    No Known Activations