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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1140
    Prev
    Next
    INDEX
    Explanations

    instances of the word "close" and its variations, indicating a focus on closure or confinement

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

    "closed" or "close"

    np_acts-logits-general · gemini-2.0-flash

    closing and closed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Brandt
    -0.62
    ]--;
    -0.62
    PhysRev
    -0.59
    🏼
    -0.54
    iw
    -0.54
    glClear
    -0.49
    TypedDataSet
    -0.48
     Starlight
    -0.48
    漿
    -0.48
    ürn
    -0.47
    POSITIVE LOGITS
     Closed
    0.99
     closes
    0.97
     closed
    0.97
    閉
    0.95
    Closed
    0.95
     clos
    0.92
     doors
    0.92
     shut
    0.92
     Shut
    0.91
     closing
    0.90
    Activations Density 0.094%

    No Known Activations