© 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. 16150
    Prev
    Next
    INDEX
    Explanations

    phrases related to methods and processes

    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
     CURIAM
    -0.50
    #![
    -0.43
     ovunque
    -0.39
    はじめに
    -0.38
     nell
    -0.37
     someplace
    -0.35
     Infórmanos
    -0.35
     negli
    -0.35
    arschijnlijk
    -0.35
    はどこ
    -0.34
    POSITIVE LOGITS
     waarin
    1.60
     wherein
    1.57
    wherein
    1.21
     जिसमें
    1.07
     whereby
    1.05
     worin
    0.80
     בו
    0.75
     jossa
    0.74
     waarbij
    0.73
     فيه
    0.63
    Activations Density 0.629%

    No Known Activations