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. 5
    Prev
    Next
    INDEX
    Explanations

    attends to the same closing curly brace characters from various points based on the opening braces preceding them

    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
    1:0.05
    2:0.05
    3:0.04
    4:0.02
    5:0.72
    6:0.04
    7:0.04
    Negative Logits
    	
    -0.71
    		
    -0.70
    			
    -0.68
     myſelf
    -0.62
    				
    -0.59
     itſelf
    -0.57
    					
    -0.56
    								
    -0.56
    							
    -0.54
    						
    -0.53
    POSITIVE LOGITS
     of
    0.31
     and
    0.31
    -
    0.31
     for
    0.30
    /
    0.30
    for
    0.29
     until
    0.29
    if
    0.29
     to
    0.28
     –
    0.28
    Activations Density 0.508%

    No Known Activations