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. 14514
    Prev
    Next
    INDEX
    Explanations

    programming syntax, particularly related to function definitions and method calls

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

    Code-related punctuation (parentheses, quotes, semicolons)

    np_acts-logits-general · gemini-2.0-flash

    code statement endings

    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
      
    -0.93
       
    -0.83
         
    -0.69
    	
    -0.67
     
    
    -0.65
        
    -0.65
    ↵↵↵
    -0.63
          
    -0.60
           
    -0.60
    oneofs
    -0.59
    POSITIVE LOGITS
    '>
    
    0.73
     devriez
    0.70
    ?),
    0.69
    '):
    
    0.69
    )");
    
    0.68
    ?«
    0.67
    ?</
    0.67
    ?):
    0.66
    %?
    0.65
     ||
    
    0.64
    Activations Density 0.192%

    No Known Activations