© 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 - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 9264
    Prev
    Next
    INDEX
    Explanations

    references to "main" functions or methods in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -1.00
    AxisSize
    -0.75
    omitempty
    -0.65
    Espèce
    -0.62
    odied
    -0.62
    matchCondition
    -0.61
    клопе
    -0.61
     Jacobsen
    -0.59
    xase
    -0.59
    kadot
    -0.58
    POSITIVE LOGITS
    main
    2.75
    MAIN
    1.82
    Main
    1.81
     Main
    1.61
    mains
    1.55
     MAIN
    1.41
    getMain
    1.17
     main
    1.13
     mains
    1.09
     Mains
    1.07
    Activations Density 0.100%

    No Known Activations