© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2933
    Prev
    Next
    INDEX
    Explanations

    language related to wealth, luxury, and high-value possessions

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

    wealthy people and luxury items

    np_acts-logits-general · gemini-2.0-flash

    wealthy, luxury, or extravagant things

    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
    ंदीखरीदारी
    -0.57
    Morfologia
    -0.50
    NotNil
    -0.44
     Sucher
    -0.44
    AccessorTable
    -0.43
    chtend
    -0.43
    gbaar
    -0.42
    erequisite
    -0.42
     Meister
    -0.41
    
    -0.41
    POSITIVE LOGITS
     luxury
    0.70
    Luxury
    0.62
     opulent
    0.61
     mewah
    0.61
     luxurious
    0.60
    luxury
    0.59
     Luxury
    0.57
     luxus
    0.56
     lavish
    0.56
     luks
    0.54
    Activations Density 0.188%

    No Known Activations