© 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 EvalsExportsinterp-engineNEWAPI 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. 6066
    Prev
    Next
    INDEX
    Explanations

    elements of code related to programming structures and their definitions

    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
     Pac
    -0.35
    共
    -0.35
    //
    -0.34
     MessageBoxIcon
    -0.34
    <!--[
    -0.32
    Dare
    -0.32
     contr
    -0.31
     Dare
    -0.31
     Library
    -0.30
     folk
    -0.30
    POSITIVE LOGITS
     AssemblyCulture
    0.63
     Numerade
    0.61
    Erreferentziak
    0.55
    ágenes
    0.55
     jadx
    0.55
    Bakgrunnsstoff
    0.54
    锈钢
    0.54
    BUG
    0.53
    printk
    0.53
    Reactivity
    0.53
    Activations Density 1.193%

    No Known Activations