© 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-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9498
    Prev
    Next
    INDEX
    Explanations

    patterns related to code blocks or structured formatting in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſſung
    -0.99
    нгред
    -0.97
    ThroughAttribute
    -0.97
     vooz
    -0.96
     للاسماء
    -0.96
    iſchen
    -0.94
    <unused68>
    -0.94
    [@BOS@]
    -0.94
    <unused14>
    -0.93
    <unused16>
    -0.93
    POSITIVE LOGITS
         
    1.05
             
    0.87
                 
    0.85
        
    0.82
                     
    0.81
                         
    0.80
           
    0.80
          
    0.79
                        
    0.75
            
    0.74
    Activations Density 0.117%

    No Known Activations