© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 94293
    Prev
    Next
    INDEX
    Explanations

    commands or instructions related to coding practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    DO NOT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.64
     térmica
    -0.59
     jadx
    -0.56
    Tracce
    -0.53
     AssemblyCulture
    -0.53
     desvan
    -0.50
     romántica
    -0.48
     tchèque
    -0.48
    knapp
    -0.47
     saludable
    -0.46
    POSITIVE LOGITS
    DO
    2.34
     DO
    2.14
    Do
    1.11
     Do
    1.10
    DOF
    1.03
    do
    0.95
     Doo
    0.94
    Doo
    0.94
     doa
    0.91
    DOS
    0.88
    Activations Density 0.008%

    No Known Activations