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. 18-GEMMASCOPE-RES-16K
    6. 10509
    Prev
    Next
    INDEX
    Explanations

    references to expensive locations and socioeconomic status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BackStack
    -0.66
     optique
    -0.60
     fondamentali
    -0.59
    RenderAtEndOf
    -0.57
     commerciali
    -0.56
    ImageContext
    -0.56
    setDo
    -0.55
     guitare
    -0.55
     universale
    -0.55
    dataflow
    -0.54
    POSITIVE LOGITS
     luxury
    1.79
     luxurious
    1.54
    luxury
    1.50
     Luxury
    1.48
     wealthy
    1.48
    Luxury
    1.44
     luxe
    1.36
     aristocratic
    1.33
     elite
    1.32
     affluent
    1.30
    Activations Density 0.590%

    No Known Activations