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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 14680
    Prev
    Next
    INDEX
    Explanations

    programming or coding constructs and their properties

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

    Code or programming-related keywords

    np_acts-logits-general · gemini-2.0-flash

    code syntax and abstract syntax trees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -1.00
       
    -0.79
           
    -0.67
        
    -0.66
         
    -0.66
    	
    -0.63
             
    -0.62
    ↵↵↵
    -0.60
                                   
    -0.60
    		
    -0.58
    POSITIVE LOGITS
    Autoritní
    0.77
    tanleria
    0.77
     $_"
    0.76
     AspNetCore
    0.70
    ագրություններ
    0.70
     nakalista
    0.69
    !")
    
    0.69
    لينكات
    0.69
    .";
    
    0.69
    */;
    0.68
    Activations Density 0.291%

    No Known Activations