© 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 EvalsExportsAPI 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. 36424
    Prev
    Next
    INDEX
    Explanations

    references to a specific name, "Rich," and related formats or names

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

    the word "Rich"

    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
     NSP
    -0.48
     Spalding
    -0.48
     Zweig
    -0.47
     Motorola
    -0.47
    )=>{
    -0.46
    kovsky
    -0.46
     Kloster
    -0.46
     CRL
    -0.46
     BSA
    -0.46
     CV
    -0.46
    POSITIVE LOGITS
     Rich
    1.90
    Rich
    1.88
     RICH
    1.43
    RICH
    1.26
    rich
    1.00
     rich
    0.98
     richer
    0.90
    Richie
    0.90
     Riche
    0.90
     Richie
    0.90
    Activations Density 0.003%

    No Known Activations