© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5419
    Prev
    Next
    INDEX
    Explanations

    color-related descriptions, particularly focusing on the color black

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

    "black" or "dark"

    np_acts-logits-general · gemini-2.0-flash

    dark colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     müſſen
    -0.69
    󠀠
    -0.68
    Rptr
    -0.67
     queſto
    -0.67
     パンチラ
    -0.66
    <unused51>
    -0.66
    <unused42>
    -0.66
    <unused28>
    -0.65
    [@BOS@]
    -0.65
    <pad>
    -0.65
    POSITIVE LOGITS
     dark
    0.96
     black
    0.89
     Black
    0.89
     darkness
    0.86
    Black
    0.85
     Dark
    0.84
     BLACK
    0.84
    black
    0.84
    dark
    0.81
    Dark
    0.80
    Activations Density 0.515%

    No Known Activations