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. 8661
    Prev
    Next
    INDEX
    Explanations

    indicators of support or emphasis for local or independent businesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    出版年
    -1.04
    ⋙
    -1.04
    ՚
    -0.99
    .",
    
    -0.96
     nakalista
    -0.95
    tvguidetime
    -0.92
    )");
    
    -0.91
    "):
    
    -0.90
    LLocation
    -0.89
    ($__
    -0.85
    POSITIVE LOGITS
      
    1.85
       
    1.57
                                   
    1.45
               
    1.32
          
    1.29
           
    1.29
         
    1.28
                 
    1.26
             
    1.25
                      
    1.23
    Activations Density 0.328%

    No Known Activations