© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 53204
    Prev
    Next
    INDEX
    Explanations

    instances of the word "spotlight" and variations, as well as phrases related to scrutiny or examination

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

    spotlight or scrutiny

    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
     Infórmanos
    -0.57
    GEBURTSDATUM
    -0.47
    httphttps
    -0.46
     <>",
    -0.44
     informée
    -0.44
     Administrativna
    -0.43
     rempliss
    -0.42
     NSCoder
    -0.42
     køb
    -0.42
    etcode
    -0.41
    POSITIVE LOGITS
     spotlight
    1.17
     Spotlight
    1.02
    spotlight
    0.97
    utiny
    0.93
    Spotlight
    0.92
     spotlights
    0.91
     scrutiny
    0.85
     limelight
    0.77
     attention
    0.73
     scrutin
    0.73
    Activations Density 0.006%

    No Known Activations