© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12382
    Prev
    Next
    INDEX
    Explanations

    references to the color white in various contexts

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

    "white"

    np_acts-logits-general · gemini-2.0-flash

    white followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    relationship
    -0.60
     Journeys
    -0.56
     ويكيپيديا
    -0.53
     geschehen
    -0.52
    ScopeManager
    -0.52
    Tikang
    -0.52
    ukunft
    -0.52
    Rohy
    -0.51
    capulco
    -0.51
    decade
    -0.51
    POSITIVE LOGITS
    White
    1.25
     White
    1.23
     white
    1.19
    white
    1.17
     WHITE
    1.11
     Putih
    1.08
    WHITE
    1.08
     whites
    0.90
     Whites
    0.90
    Whites
    0.88
    Activations Density 0.133%

    No Known Activations