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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 3456
    Prev
    Next
    INDEX
    Explanations

    blocks of repeated characters or symbols that are formatted in a specific way

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.90
    formKey
    -0.79
    featureID
    -0.78
     rhestr
    -0.74
     Cline
    -0.74
     EClass
    -0.74
    Попис
    -0.71
    Cubit
    -0.71
    complexContent
    -0.69
     Kalyan
    -0.69
    POSITIVE LOGITS
                        
    1.88
    1.50
                         
    1.46
                       
    1.43
                          
    1.39
                      
    1.34
                            
    1.33
                    
    1.31
                                
    1.25
                           
    1.23
    Activations Density 0.046%

    No Known Activations