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. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 195
    Prev
    Next
    INDEX
    Explanations

    attends to the term "business" from terminal punctuation or other non-business-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.04
    2:0.05
    3:0.54
    4:0.05
    5:0.03
    6:0.13
    7:0.11
    Negative Logits
    ↵
    -0.29
    		
    -0.26
    				
    -0.25
    	
    -0.23
                    
    -0.22
        
    -0.22
            
    -0.22
                                   
    -0.22
    					
    -0.21
    			
    -0.21
    POSITIVE LOGITS
     disambiguazione
    0.42
     EconPapers
    0.40
    verwijspagina
    0.37
    rouvez
    0.37
     विश्वसनीयता
    0.36
     >=",
    0.35
    KURZBESCHREIBUNG
    0.34
    principalTable
    0.33
    ViewFeatures
    0.33
     للاسماء
    0.33
    Activations Density 1.837%

    No Known Activations