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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6007
    Prev
    Next
    INDEX
    Explanations

    the presence of large blocks of whitespace or separator characters in a document

    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
    AsUp
    -0.87
    createCanvas
    -0.86
    endmodule
    -0.79
     GlobalKey
    -0.76
    mybatisplus
    -0.75
    bodyParser
    -0.75
     Dara
    -0.75
    gatsby
    -0.72
    featureID
    -0.71
     JTable
    -0.71
    POSITIVE LOGITS
                                
    1.99
    1.77
                               
    1.62
                                 
    1.61
                              
    1.53
                                  
    1.51
                             
    1.50
                            
    1.37
                          
    1.35
                         
    1.32
    Activations Density 0.118%

    No Known Activations