© 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. 15634
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "black."

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

    "black"

    np_acts-logits-general · gemini-2.0-flash

    black adjective

    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
     itemView
    -0.65
    VIAF
    -0.62
     Vibe
    -0.61
     Vantage
    -0.58
    vibe
    -0.57
    opsida
    -0.50
    seido
    -0.50
     evt
    -0.50
    tableFuture
    -0.50
     Vibes
    -0.50
    POSITIVE LOGITS
     Black
    0.86
     BLACK
    0.84
    Black
    0.81
     black
    0.77
    black
    0.73
    BLACK
    0.72
     Block
    0.71
    Block
    0.70
     Cár
    0.65
    block
    0.63
    Activations Density 0.097%

    No Known Activations