© 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. 6-GEMMASCOPE-RES-16K
    11. 11791
    Prev
    Next
    INDEX
    Explanations

    the word "main" and its derivatives, indicating a focus on primary concepts or key elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phénom
    -0.70
    tinyos
    -0.68
     numérique
    -0.67
     Fleck
    -0.67
     picioare
    -0.65
    彿
    -0.64
    ️
    -0.64
     contemporain
    -0.64
     Nunn
    -0.64
     ibi
    -0.63
    POSITIVE LOGITS
     main
    2.10
     Main
    1.97
     MAIN
    1.91
    Main
    1.83
    MAIN
    1.77
    main
    1.65
     Haupt
    1.49
     głów
    1.45
    getMain
    1.39
     mains
    1.38
    Activations Density 0.046%

    No Known Activations