© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4954
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "gs," likely indicating a specific technical term

    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
     Wester
    -0.43
     Stahl
    -0.40
    ЖА
    -0.40
    riften
    -0.38
    envolvimento
    -0.37
     Planet
    -0.37
     pourrez
    -0.37
     cometer
    -0.36
    สิ
    -0.36
    NSInteger
    -0.36
    POSITIVE LOGITS
    gs
    0.83
    GS
    0.76
     الحره
    0.75
     gs
    0.72
     GS
    0.71
    webElementXpaths
    0.70
     հղումներ
    0.59
     Crown
    0.56
     للاسماء
    0.55
    ロウィン
    0.54
    Activations Density 0.542%

    No Known Activations