© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1709
    Prev
    Next
    INDEX
    Explanations

    structured data or code blocks, particularly in a programming or markup context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.82
     "
    -0.65
    canyon
    -0.64
    (!__
    -0.60
     cam
    -0.60
    PreferredItem
    -0.60
     ver
    -0.59
    ']))
    -0.59
    gameserver
    -0.59
    SharedDtor
    -0.59
    POSITIVE LOGITS
                
    2.28
                                
    1.79
                 
    1.77
               
    1.73
                  
    1.70
    1.68
              
    1.65
                        
    1.58
                    
    1.57
                   
    1.57
    Activations Density 0.135%

    No Known Activations