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

    Neuronpedia

    Jacobian LensNEW
    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. 8819
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to abstract syntax trees (ASTs) in programming 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
     Réponses
    -0.76
    enumi
    -0.72
    awtextra
    -0.71
    enumii
    -0.69
    :✨
    -0.68
    WithIOException
    -0.68
    ьаж
    -0.67
     EconPapers
    -0.66
    yip
    -0.65
     MediatR
    -0.65
    POSITIVE LOGITS
     Ov
    0.57
    Ov
    0.55
     ov
    0.55
     Quin
    0.54
     }}"></
    0.54
     Maynard
    0.54
     dépens
    0.52
     regroupe
    0.50
     fiscale
    0.50
     Tor
    0.49
    Activations Density 0.061%

    No Known Activations