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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 1693
    Prev
    Next
    INDEX
    Explanations

    terms related to wholesale clothing and bulk purchasing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mergeFrom
    -0.54
    Autoritní
    -0.51
    providedIn
    -0.47
    ตร์
    -0.46
    بق
    -0.45
    bergh
    -0.44
     autorytatywna
    -0.43
    bodyParser
    -0.40
    coher
    -0.40
    argent
    -0.39
    POSITIVE LOGITS
     suppliers
    1.25
     wholesale
    1.16
     supplier
    1.09
     wholesalers
    1.07
    suppliers
    1.04
     Suppliers
    1.03
    Wholesale
    1.02
    wholesale
    1.00
     sourcing
    0.98
     wholesaler
    0.97
    Activations Density 0.256%

    No Known Activations