© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9285
    Prev
    Next
    INDEX
    Explanations

    references to buildings

    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
    IContainer
    -0.56
    tispiece
    -0.55
    Див
    -0.54
    Begriffsklä
    -0.53
    goku
    -0.50
    hasNext
    -0.49
     cane
    -0.49
    AnimationFrame
    -0.49
    ragos
    -0.49
    IPCC
    -0.49
    POSITIVE LOGITS
    setVerticalGroup
    0.72
    Building
    0.68
     Building
    0.68
     Stray
    0.66
    Gram
    0.61
    TAGS
    0.61
    Topping
    0.60
    BorderFactory
    0.60
     Topping
    0.60
     Gram
    0.59
    Activations Density 0.031%

    No Known Activations