© 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 - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5882
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and components, particularly those associated with button actions and UI elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.75
     Paglinawan
    -0.71
     gynhyrchwyd
    -0.69
    RegistryLite
    -0.68
     protoimpl
    -0.67
    IsContent
    -0.66
    errHandler
    -0.64
     CreateTagHelper
    -0.63
    IndentedString
    -0.62
     uintptr
    -0.62
    POSITIVE LOGITS
     button
    0.88
     buttons
    0.88
    ActionButton
    0.87
    JButton
    0.82
    IBarButtonItem
    0.81
     btn
    0.80
    button
    0.79
     JButton
    0.79
    NegativeButton
    0.71
     Button
    0.70
    Activations Density 0.219%

    No Known Activations