© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 7340
    Prev
    Next
    INDEX
    Explanations

    references to societal inequality and class distinctions

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

    wealth, refinement, or high quality

    np_acts-logits-general · gemini-2.0-flash

    high quality and expensive items

    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
     prácti
    -0.67
    AndEndTag
    -0.66
     praktische
    -0.66
     semplici
    -0.65
     praktischen
    -0.65
    Practical
    -0.64
    dymyr
    -0.63
     amitié
    -0.61
     amizade
    -0.59
     Practical
    -0.58
    POSITIVE LOGITS
     luxury
    1.04
     elite
    1.03
     luxurious
    1.01
     expensive
    0.98
     premium
    0.95
     fancy
    0.95
     posh
    0.95
     upscale
    0.94
    luxury
    0.92
     high
    0.89
    Activations Density 0.484%

    No Known Activations