© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13265
    Prev
    Next
    INDEX
    Explanations

    the word "main."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     Grüsse
    -0.44
    iempos
    -0.44
     Wikimedijinoj
    -0.43
     actionTypes
    -0.40
    ercise
    -0.39
    Oggi
    -0.39
    Hentet
    -0.39
     rospy
    -0.38
    reactstrap
    -0.38
    atorship
    -0.37
    POSITIVE LOGITS
     main
    4.31
    main
    3.58
     Main
    3.44
    Main
    3.39
     MAIN
    3.34
    MAIN
    3.14
    getMain
    2.47
     głów
    2.42
    メイン
    2.41
     hlavní
    2.34
    Activations Density 0.128%

    No Known Activations