© 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. 38-GEMMASCOPE-RES-16K
    11. 11320
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes over time and their implications

    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
     propOrder
    -0.73
    RTLR
    -0.72
    SourceChecksum
    -0.63
     AssemblyCulture
    -0.62
     kaarangay
    -0.62
    UrlResolution
    -0.61
    +#+#
    -0.61
    oredCriteria
    -0.61
    SharedDtor
    -0.61
    անում
    -0.61
    POSITIVE LOGITS
     has
    2.39
     have
    1.87
     telah
    1.77
    has
    1.47
     đã
    1.45
     heeft
    1.38
    Has
    1.36
     Has
    1.25
     έχει
    1.24
     hath
    1.19
    Activations Density 4.421%

    No Known Activations