© 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. 15885
    Prev
    Next
    INDEX
    Explanations

    attributes and parameters related to drawing or graphical representation in technical specifications

    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
    parsedMessage
    -0.74
    +#+
    -0.60
    tableFuture
    -0.59
    bolista
    -0.57
     AssemblyCompany
    -0.57
     $_"
    -0.57
    Попис
    -0.57
    ientras
    -0.56
     tartalo
    -0.56
     ſelb
    -0.56
    POSITIVE LOGITS
     width
    1.33
    width
    1.03
     Width
    0.75
    Width
    0.74
     largeur
    0.64
     widths
    0.62
    宽度
    0.60
     ширина
    0.58
     WIDTH
    0.58
     height
    0.55
    Activations Density 0.133%

    No Known Activations