Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5991
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to wealth, luxury, and exclusivity

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

    Luxury or exclusive items/locations

    np_acts-logits-general · gemini-2.0-flash

    luxury and exclusivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autocollant
    -0.65
    ScopeManager
    -0.58
    ImageContext
    -0.58
     volontaire
    -0.56
     guitare
    -0.56
     lanterna
    -0.52
     maïs
    -0.51
    PullParser
    -0.51
     bénévol
    -0.51
    ırlı
    -0.50
    POSITIVE LOGITS
     luxury
    1.27
     luxurious
    1.10
     opulent
    1.07
     Luxury
    1.04
    luxury
    1.03
    Luxury
    1.02
     caviar
    0.97
     bespoke
    0.95
     luxe
    0.94
     lavish
    0.89
    Activations Density 0.344%

    No Known Activations