© 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. 13248
    Prev
    Next
    INDEX
    Explanations

    attributes related to color and darkness

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

    "black" or related words

    np_acts-logits-general · gemini-2.0-flash

    black and dark

    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
    ніципалі
    -0.75
     AssemblyCompany
    -0.75
     ProtoMessage
    -0.66
    StructEnd
    -0.66
    Cyfarwyddwr
    -0.65
    OGND
    -0.65
    rungsseite
    -0.65
     müſſen
    -0.64
     パンチラ
    -0.63
     queſto
    -0.61
    POSITIVE LOGITS
     dark
    1.03
     darkness
    0.92
    dark
    0.92
     Dark
    0.90
    Dark
    0.88
     darkest
    0.85
     black
    0.84
     DARK
    0.83
     oscuro
    0.82
     darker
    0.81
    Activations Density 0.488%

    No Known Activations