© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 702
    Prev
    Next
    INDEX
    Explanations

    elements related to unsettling or bizarre themes

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

    associated with unsettling or creepy things

    np_acts-logits-general · gemini-2.0-flash

    disturbing creepy eerie weird

    np_acts-logits-general · gemini-2.5-flash-lite

    unsettling, horror-tinged content and reactions—expressions of fear, revulsion, obsession, and morbid or grotesque imagery.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     للمعارف
    -0.63
     transfieras
    -0.61
    oa̍t
    -0.57
     للاسماء
    -0.52
    ьаж
    -0.52
    httphttps
    -0.52
    ftagPool
    -0.50
    spesies
    -0.49
     surla
    -0.49
    sprit
    -0.49
    POSITIVE LOGITS
     creepy
    0.64
     eerie
    0.59
    creepy
    0.57
     sinister
    0.52
     inquiet
    0.48
    Creepy
    0.48
     creep
    0.47
     omin
    0.45
     weird
    0.44
     weir
    0.43
    Activations Density 0.412%

    No Known Activations