© 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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7659
    Prev
    Next
    INDEX
    Explanations

    mentions of application-related terms, specifically those related to the structure and components of software applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sauvages
    -0.82
     blanches
    -0.71
     vectorielles
    -0.70
     blessé
    -0.68
     remporté
    -0.68
     polaire
    -0.64
     étoit
    -0.62
     étoient
    -0.60
     russes
    -0.60
     bílá
    -0.59
    POSITIVE LOGITS
     App
    1.24
     app
    1.08
    App
    0.94
    GEBURTSDATUM
    0.80
    app
    0.76
    GroupLayout
    0.74
    yntaxException
    0.73
    NameInMap
    0.71
    LayoutStyle
    0.69
     AssemblyTitle
    0.69
    Activations Density 0.123%

    No Known Activations