© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 37748
    Prev
    Next
    INDEX
    Explanations

    references to New Orleans and its historical significance

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

    Louisiana places and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idyl
    -0.39
     Guadalajara
    -0.38
     onCancelled
    -0.36
     Ontario
    -0.36
    SqlSession
    -0.35
     yogur
    -0.35
    WebElementEntity
    -0.35
     AspNetCore
    -0.34
     cider
    -0.34
    Skocz
    -0.34
    POSITIVE LOGITS
     Louisiana
    1.52
    Louisiana
    1.48
     LSU
    1.15
     Cajun
    1.07
     Bayou
    1.06
    LSU
    1.02
     Tulane
    1.02
     Shreveport
    1.00
     Baton
    1.00
     Mardi
    0.93
    Activations Density 0.147%

    No Known Activations