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. 5-GEMMASCOPE-RES-16K
    6. 11169
    Prev
    Next
    INDEX
    Explanations

    mathematical constructs and relationships related to dimensions and vector spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.90
     ContentValues
    -0.88
    initializeApp
    -0.84
     joaat
    -0.76
    tonode
    -0.76
     NOL
    -0.75
    !")
    
    -0.73
     BoxFit
    -0.71
     ROL
    -0.70
     MessageBoxIcon
    -0.69
    POSITIVE LOGITS
    ↵
    1.04
    		
    0.90
    [toxicity=0]
    0.88
    	
    0.87
        
    0.85
            
    0.85
          
    0.82
    			
    0.81
       
    0.78
    ↵↵↵
    0.78
    Activations Density 0.245%

    No Known Activations