© 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. 3-GEMMASCOPE-RES-16K
    11. 10334
    Prev
    Next
    INDEX
    Explanations

    patterns and structures related to coding syntax, specifically in JSON or similar data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    “
    -0.48
     Verfügung
    -0.40
    čić
    -0.36
    Chham
    -0.35
     Entwicklung
    -0.35
     privil
    -0.33
     nimic
    -0.33
    aVar
    -0.33
    balleur
    -0.32
     Stedman
    -0.32
    POSITIVE LOGITS
    =(
    1.53
    =[
    1.50
    ={
    1.29
    =-
    1.23
    =%
    1.22
    =(-
    1.17
    =(\
    1.12
    =${
    1.09
    =['
    1.06
    =*
    1.05
    Activations Density 0.267%

    No Known Activations