© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5132
    Prev
    Next
    INDEX
    Explanations

    syntactical structure and function within code

    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
    expandindo
    -0.55
     AssemblyVersion
    -0.52
     GenerationType
    -0.52
    كويكب
    -0.51
     AssemblyTitle
    -0.50
    ँ
    -0.50
     Wikiseite
    -0.50
    angliski
    -0.49
     تكبرها
    -0.49
     Auffassung
    -0.48
    POSITIVE LOGITS
      
    0.86
          
    0.75
       
    0.52
    
    0.49
    <h5>
    0.45
              
    0.43
    FIG
    0.36
     Folks
    0.35
     Afterward
    0.33
         
    0.32
    Activations Density 0.117%

    No Known Activations