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. 5-GEMMASCOPE-RES-16K
    6. 4275
    Prev
    Next
    INDEX
    Explanations

    features and specifications related to telecommunications products and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.89
    存于互联网档案馆
    -0.78
    runApp
    -0.74
     StatefulWidget
    -0.73
     mxArray
    -0.72
    endphp
    -0.71
     AssemblyTitle
    -0.70
     StatelessWidget
    -0.70
     betweenstory
    -0.69
    writeFieldEnd
    -0.66
    POSITIVE LOGITS
     broadband
    0.84
     Telecom
    0.80
     Broadband
    0.77
     telecom
    0.73
    Verizon
    0.63
    telecom
    0.60
     Airtel
    0.60
     internet
    0.59
     Internet
    0.59
     Verizon
    0.57
    Activations Density 0.195%

    No Known Activations