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. 11-GEMMASCOPE-RES-16K
    6. 5585
    Prev
    Next
    INDEX
    Explanations

    references to human resources and employee management concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.78
    شهاد
    -0.60
     consultato
    -0.55
    --){
    -0.52
     Clar
    -0.49
     createStore
    -0.48
    SuccessListener
    -0.48
    Studios
    -0.48
    TestMethod
    -0.48
    gemar
    -0.48
    POSITIVE LOGITS
     payroll
    0.98
     Payroll
    0.97
     HR
    0.97
    payroll
    0.87
    Payroll
    0.86
     recruitment
    0.81
    HR
    0.80
     Recruitment
    0.80
     employee
    0.79
    Employers
    0.77
    Activations Density 0.302%

    No Known Activations