© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3114
    Prev
    Next
    INDEX
    Explanations

    elements related to performance metrics and parameters in a code or computational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    లాలు
    -0.48
     мәкал
    -0.45
    uxxxx
    -0.41
    Havolalar
    -0.40
    contd
    -0.40
    ๆ
    -0.40
     geheel
    -0.38
     Thu
    -0.38
    !"
    -0.37
    oa̍t
    -0.37
    POSITIVE LOGITS
                
    0.94
                    
    0.85
              
    0.83
                        
    0.81
                  
    0.78
            
    0.75
               
    0.74
                      
    0.73
                   
    0.73
                            
    0.71
    Activations Density 0.180%

    No Known Activations