© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10341
    Prev
    Next
    INDEX
    Explanations

    questions or queries regarding understanding and knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dAtA
    -0.43
    Lähteet
    -0.42
    وردار
    -0.38
    位
    -0.38
     Wikimedijinoj
    -0.37
    thâu
    -0.37
    ViewImports
    -0.35
     contr
    -0.34
     uti
    -0.33
    IBOutlet
    -0.33
    POSITIVE LOGITS
     happening
    1.40
     Happening
    1.03
     wrong
    0.99
    happ
    0.88
     occurring
    0.84
    wrong
    0.81
     terjadi
    0.77
     happened
    0.77
     happen
    0.75
     amiss
    0.73
    Activations Density 0.197%

    No Known Activations