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. 16-GEMMASCOPE-RES-16K
    6. 12668
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation in an equation

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

    Mathematical or symbolic notation

    np_acts-logits-general · gemini-2.0-flash

    special characters and math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.79
     FontWeight
    -0.67
    formKey
    -0.64
    MethodImpl
    -0.61
     RoutedEventArgs
    -0.61
    DebuggerNonUser
    -0.59
    labelledby
    -0.59
     rolls
    -0.58
    Lähteet
    -0.58
     =>
    
    -0.56
    POSITIVE LOGITS
    	
    0.72
       
    0.70
        
    0.69
    人民共和国
    0.69
    		
    0.69
      
    0.68
     quæ
    0.68
          
    0.67
     daß
    0.66
                                  
    0.65
    Activations Density 0.348%

    No Known Activations