© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 259
    Prev
    Next
    INDEX
    Explanations

    references to the color red, particularly in varying contexts or phrases

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

    "Red" followed by various nouns

    np_acts-logits-general · gemini-2.0-flash

    Red + (Sox, Cross, River, Kite, herring)

    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
    ConstraintMaker
    -0.86
    RectangleBorder
    -0.78
    AccessorTable
    -0.75
    elemField
    -0.63
    Autoritní
    -0.59
    клопе
    -0.57
    makeConstraints
    -0.57
    ValueStyle
    -0.57
    Espèce
    -0.57
     AssemblyCompany
    -0.56
    POSITIVE LOGITS
     Red
    0.88
     RED
    0.86
    Red
    0.78
     レッド
    0.73
     red
    0.71
     rosse
    0.64
     erythro
    0.63
     vermelho
    0.62
     vermelha
    0.62
    oub
    0.62
    Activations Density 0.065%

    No Known Activations