© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10271
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "fill" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GroupLayout
    -0.75
    Vidite
    -0.61
    antMatchers
    -0.61
     sph
    -0.60
     ControllerBase
    -0.60
    InitVars
    -0.60
     estimés
    -0.59
    isGrid
    -0.58
     ویکی‌پدیا
    -0.58
     propOrder
    -0.57
    POSITIVE LOGITS
     fill
    1.22
     filled
    1.09
    fill
    1.07
    Fill
    1.04
     Fill
    0.98
     fills
    0.94
    filled
    0.93
     FILL
    0.88
    fills
    0.84
     Filled
    0.83
    Activations Density 0.072%

    No Known Activations