© 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. 20-GEMMASCOPE-RES-16K
    11. 12027
    Prev
    Next
    INDEX
    Explanations

    items and features related to garage doors and their mechanisms

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

    Window coverings and garage doors

    np_acts-logits-general · gemini-2.0-flash

    window coverings and doors

    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
    NameInMap
    -0.54
    FieldNumber
    -0.52
    .~(\
    -0.52
     heapq
    -0.51
     Wiktionnaire
    -0.50
     EconPapers
    -0.49
     kPa
    -0.49
    ResponseBody
    -0.49
    acke
    -0.48
     Backpack
    -0.48
    POSITIVE LOGITS
     shutters
    1.00
     blinds
    0.77
     curtains
    0.75
     Venetian
    0.74
     Shutter
    0.70
     door
    0.70
     shutter
    0.70
     curtain
    0.69
     sliding
    0.68
     Blinds
    0.67
    Activations Density 0.105%

    No Known Activations