© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 70616
    Prev
    Next
    INDEX
    Explanations

    celestial phenomena and nighttime imagery

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

    night sky, stars, and celestial events

    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
     VIDEOTAPE
    -0.37
     Polo
    -0.31
    Dragons
    -0.30
     обратить
    -0.30
     colgantes
    -0.30
    社
    -0.29
    出場
    -0.29
     keber
    -0.29
     appearances
    -0.29
    пере
    -0.29
    POSITIVE LOGITS
    principalColumn
    0.62
     للمعارف
    0.60
     ujednoznacz
    0.60
     nahilalakip
    0.59
    AndEndTag
    0.59
     night
    0.59
     '\\;'
    0.58
     nights
    0.57
    IndentedString
    0.55
     désert
    0.54
    Activations Density 0.008%

    No Known Activations