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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 724
    Prev
    Next
    INDEX
    Explanations

    references to online marketplaces and ecommerce platforms

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

    links to online shops or listings

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

    Etsy and handmade goods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    XmlAccessType
    -0.83
     arşivlendi
    -0.64
    BagConstraints
    -0.59
     Continuum
    -0.58
    AsUp
    -0.56
    avadoc
    -0.56
     cir
    -0.55
     Esposito
    -0.55
     Telex
    -0.54
    |/
    -0.53
    POSITIVE LOGITS
     Etsy
    1.01
     etsy
    0.97
    Etsy
    0.87
    etsy
    0.78
     handmade
    0.72
     shop
    0.64
     custom
    0.62
     personalised
    0.57
     COPYRIGHT
    0.57
     designs
    0.56
    Activations Density 0.061%

    No Known Activations