© 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. 2-GEMMASCOPE-RES-16K
    11. 8483
    Prev
    Next
    INDEX
    Explanations

    patterns or structures within text data, particularly focusing on sequences or block elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.80
    UserScript
    -0.61
    ThroughAttribute
    -0.59
    moveToFirst
    -0.58
    WebServlet
    -0.56
     للاسماء
    -0.56
    RUnlock
    -0.55
    setWeight
    -0.54
    RTLU
    -0.54
    GEBURTS
    -0.54
    POSITIVE LOGITS
          
    1.17
           
    1.15
       
    1.15
              
    1.12
                      
    1.09
                          
    0.93
                       
    0.92
             
    0.92
                  
    0.88
                   
    0.85
    Activations Density 0.334%

    No Known Activations