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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2519
    Prev
    Next
    INDEX
    Explanations

    phrases related to shipping and delivery times

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

    Time periods (days, hours) after "next" or working"

    np_acts-logits-general · gemini-2.0-flash

    working days and hours

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     customers
    -0.65
     متعلقه
    -0.62
     Customers
    -0.59
    Customers
    -0.58
    customers
    -0.53
    ünstig
    -0.51
    Hentet
    -0.51
    Népesség
    -0.50
    //
    -0.50
     customer
    -0.50
    POSITIVE LOGITS
     business
    1.12
    business
    1.06
     working
    1.00
    Business
    0.99
     Business
    0.96
     BUSINESS
    0.96
    working
    0.95
    BUSINESS
    0.95
     WORKING
    0.94
    WORKING
    0.93
    Activations Density 0.159%

    No Known Activations