Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 12390
    Prev
    Next
    INDEX
    Explanations

    patterns related to numeric values or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.63
    __(/*!
    -0.61
    حوالہ
    -0.60
    IContainer
    -0.60
     Morse
    -0.57
    GOTREF
    -0.57
    zeman
    -0.56
     Cassidy
    -0.56
    Referanser
    -0.55
    orama
    -0.54
    POSITIVE LOGITS
    				
    0.82
    			
    0.73
    					
    0.69
    		
    0.67
    	
    0.66
     protoimpl
    0.58
    						
    0.57
     Alamo
    0.57
    							
    0.56
    ScopeManager
    0.56
    Activations Density 0.026%

    No Known Activations