© 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. 36-GEMMASCOPE-RES-16K
    11. 14890
    Prev
    Next
    INDEX
    Explanations

    technical process descriptions and terms related to functionality and compatibility

    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
     MainAxisSize
    -0.49
    afficheront
    -0.45
     дописавши
    -0.42
     ujednoznacz
    -0.41
    WebElementEntity
    -0.38
    adpleegd
    -0.35
    bootstrapcdn
    -0.35
    piecze
    -0.35
     Савезне
    -0.34
    Lugares
    -0.34
    POSITIVE LOGITS
     piece
    0.97
     hour
    0.94
     layer
    0.93
     inning
    0.93
     step
    0.93
     pixel
    0.91
     minute
    0.90
     month
    0.89
     mile
    0.89
     week
    0.87
    Activations Density 0.749%

    No Known Activations