© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10192
    Prev
    Next
    INDEX
    Explanations

    references to recreational facilities and social spaces

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

    "pool" or "pools"

    np_acts-logits-general · gemini-2.0-flash

    swimming pool

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.62
     linkovi
    -0.61
     виправивши
    -0.61
    contentLoaded
    -0.60
    invokeLater
    -0.57
    تقاوى
    -0.55
    rayage
    -0.55
    ̍t
    -0.54
     Numerology
    -0.52
     Италијани
    -0.51
    POSITIVE LOGITS
     pool
    2.48
     Pool
    2.21
    pool
    2.11
    Pool
    2.08
     POOL
    1.94
     pools
    1.93
    POOL
    1.77
     Pools
    1.77
     swimming
    1.73
    pools
    1.63
    Activations Density 0.095%

    No Known Activations