Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8416
    Prev
    Next
    INDEX
    Explanations

    references to the color yellow

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

    the color yellow

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     isKindOfClass
    -0.55
    BagConstraints
    -0.54
    хьтан
    -0.50
     doPost
    -0.46
    bondale
    -0.46
    include
    -0.45
    AnchorStyles
    -0.45
    Bris
    -0.45
    coz
    -0.44
    ({_
    -0.44
    POSITIVE LOGITS
     Yellow
    1.25
    Yellow
    1.20
     YELLOW
    1.05
     yellow
    1.05
    yellow
    0.97
    YELLOW
    0.85
     yellows
    0.82
     amarillas
    0.79
     amarilla
    0.77
     Yellowstone
    0.75
    Activations Density 0.009%

    No Known Activations