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. 20-GEMMASCOPE-RES-16K
    6. 2076
    Prev
    Next
    INDEX
    Explanations

    structural elements and formatting in technical or programming contexts

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

    Numerical or symbolic characters

    np_acts-logits-general · gemini-2.0-flash

    numbers and code snippets

    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
    <eos>
    -0.73
    ↵
    -0.70
                                   
    -0.66
     _
    -0.59
                              
    -0.59
     +
    -0.58
     om
    -0.57
     hold
    -0.57
      
    -0.56
                
    -0.56
    POSITIVE LOGITS
     مشين
    0.98
     فريبيس
    0.96
     שוליים
    0.92
    WriteTagHelper
    0.89
    endphp
    0.87
    出版年
    0.86
     الرياضيه
    0.85
    Sucesor
    0.84
     rospy
    0.84
    SBATCH
    0.84
    Activations Density 0.079%

    No Known Activations