© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14897
    Prev
    Next
    INDEX
    Explanations

    the structure and syntax of code, particularly focusing on programming language elements like braces and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets, often with import or return statements

    np_acts-logits-general · gemini-2.0-flash

    programming class structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.79
     Himo
    -0.76
    لينكات
    -0.71
     cherchés
    -0.66
    ℗
    -0.65
    éndole
    -0.64
     TextAppearance
    -0.63
    ########.
    -0.63
    $\#
    -0.62
    _${
    -0.62
    POSITIVE LOGITS
    		
    0.56
     class
    0.55
        
    0.55
             
    0.54
    ↵↵
    0.53
       
    0.52
      
    0.52
    class
    0.52
            
    0.52
         
    0.52
    Activations Density 0.143%

    No Known Activations