© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3630
    Prev
    Next
    INDEX
    Explanations

    references to richness in culture or experience

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

    the word "rich"

    np_acts-logits-general · gemini-2.0-flash

    rich qualities and abundance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    application
    -0.65
     Szy
    -0.52
     application
    -0.49
     szy
    -0.48
     Mosley
    -0.48
    action
    -0.47
     heck
    -0.47
     Heck
    -0.46
     suicide
    -0.46
    Application
    -0.46
    POSITIVE LOGITS
    riched
    0.97
    richment
    0.91
     richness
    0.81
     enriched
    0.76
     rich
    0.75
    RICH
    0.75
    rich
    0.74
     Riches
    0.74
    Rich
    0.73
     richest
    0.72
    Activations Density 0.212%

    No Known Activations