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-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65930
    Prev
    Next
    INDEX
    Explanations

    numerical values or measurements related to statistics or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.84
     Weiſe
    -0.80
    IUrlHelper
    -0.78
     $_(
    -0.77
    SequentialGroup
    -0.77
    ſſung
    -0.75
     imagui
    -0.75
    <unused68>
    -0.75
    <unused14>
    -0.75
    [@BOS@]
    -0.75
    POSITIVE LOGITS
      
    0.98
       
    0.96
        
    0.82
          
    0.70
         
    0.65
           
    0.60
            
    0.59
              
    0.59
     
    0.57
                
    0.52
    Activations Density 0.001%

    No Known Activations