Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9086
    Prev
    Next
    INDEX
    Explanations

    details about windows in architectural contexts

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

    windows or doors

    np_acts-logits-general · gemini-2.0-flash

    building openings

    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-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
    CacheManager
    -0.51
     JpaRepository
    -0.48
    nalités
    -0.47
    addAttribute
    -0.46
     Lambert
    -0.44
     acceleration
    -0.44
    setObjectName
    -0.44
    camisetas
    -0.44
     Kugel
    -0.44
    aser
    -0.43
    POSITIVE LOGITS
     window
    0.69
     Window
    0.63
     windows
    0.63
     ventana
    0.62
     WINDOW
    0.59
     jendela
    0.58
     finestra
    0.57
    Window
    0.54
     ventanas
    0.52
     fenêtre
    0.52
    Activations Density 0.097%

    No Known Activations