© 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. 20-GEMMASCOPE-RES-65K
    11. 417
    Prev
    Next
    INDEX
    Explanations

    programming constructs and keywords related to code imports and file includes

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

    occurrences of programming import statements and usage declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    BufferException
    -0.66
     utafitiHapana
    -0.61
    setVerticalGroup
    -0.57
    FunctionFlags
    -0.55
     protoimpl
    -0.53
    Personendaten
    -0.52
     AttributeSet
    -0.51
    invokeLater
    -0.51
     MainAxisSize
    -0.50
     propOrder
    -0.50
    POSITIVE LOGITS
    StoryboardSegue
    0.67
     فريبيس
    0.62
     getModel
    0.59
     Moq
    0.59
     static
    0.58
    stretchr
    0.56
    openhague
    0.52
     MOQ
    0.52
    gefahr
    0.52
     Efq
    0.49
    Activations Density 0.005%

    No Known Activations