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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 13798
    Prev
    Next
    INDEX
    Explanations

    references to luxury and high-end products or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -1.00
    
    -0.92
    fvar
    -0.87
    SequentialGroup
    -0.86
     فريبيس
    -0.85
     cardiaque
    -0.85
    RenderAtEndOf
    -0.84
    Abitanti
    -0.80
    prepareStatement
    -0.77
     AssemblyCulture
    -0.76
    POSITIVE LOGITS
     luxury
    1.43
     Luxury
    1.28
    Luxury
    1.16
    luxury
    1.16
     luxe
    1.13
     luxurious
    1.13
     luxus
    1.10
     luxo
    1.08
     luxuries
    1.07
     Luxus
    1.06
    Activations Density 0.150%

    No Known Activations