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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 36711
    Prev
    Next
    INDEX
    Explanations

    phrases related to business transactions and supply chain dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ürger
    -0.45
     intérieure
    -0.45
     crowdfunding
    -0.45
     púb
    -0.44
    джет
    -0.44
     befolk
    -0.44
     prévue
    -0.44
    CAPTCHA
    -0.44
     termica
    -0.43
     softmax
    -0.43
    POSITIVE LOGITS
     suppliers
    0.88
     supplier
    0.87
     customer
    0.82
     customers
    0.81
     referenties
    0.81
     Suppliers
    0.76
     vendor
    0.74
     proveedores
    0.74
    Билгалдахарш
    0.74
     Supplier
    0.73
    Activations Density 0.104%

    No Known Activations