© 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. 33-GEMMASCOPE-RES-16K
    11. 9947
    Prev
    Next
    INDEX
    Explanations

    patterns or structural elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     '{@
    -0.57
    RTHOOK
    -0.54
     AssemblyCulture
    -0.54
    SequentialGroup
    -0.50
     createSprite
    -0.47
    RenderAtEndOf
    -0.46
    Jîn
    -0.46
     dezelve
    -0.46
     endforeach
    -0.45
    EDEFAULT
    -0.45
    POSITIVE LOGITS
      
    1.66
       
    1.16
         
    0.88
                                   
    0.86
           
    0.85
          
    0.81
                       
    0.79
        
    0.77
                                  
    0.77
               
    0.76
    Activations Density 1.772%

    No Known Activations