© 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. 36-GEMMASCOPE-RES-16K
    11. 9232
    Prev
    Next
    INDEX
    Explanations

    numeric data and references related to court cases and legal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     One
    -1.39
    One
    -1.33
    ONE
    -1.30
     ONE
    -1.21
    one
    -1.16
    一
    -0.97
    1
    -0.87
     onep
    -0.82
     одно
    -0.74
     one
    -0.69
    POSITIVE LOGITS
    IsContent
    0.54
    HideFlags
    0.52
     }{@
    0.51
     AdapterView
    0.51
    \{\\
    0.50
    Autoritní
    0.50
    ftagPool
    0.47
     propOrder
    0.47
    styleType
    0.47
    outSlope
    0.46
    Activations Density 1.991%

    No Known Activations