© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3369
    Prev
    Next
    INDEX
    Explanations

    indications of technicality or programming-related syntax and structures

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

    Text with asterisks

    np_acts-logits-general · gemini-2.0-flash

    Mechanical equipment

    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
    存于互联网档案馆
    -0.68
     forfait
    -0.57
     aé
    -0.51
     cedo
    -0.50
    DebuggerStep
    -0.50
    チール
    -0.48
    fait
    -0.47
    fini
    -0.47
    garn
    -0.46
    entuh
    -0.46
    POSITIVE LOGITS
        
    0.75
          
    0.73
    +#+
    0.72
              
    0.69
     InputDecoration
    0.69
                  
    0.66
            
    0.66
           
    0.65
                      
    0.65
               
    0.64
    Activations Density 0.402%

    No Known Activations