Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 11566
    Prev
    Next
    INDEX
    Explanations

    segments of text that are entirely or predominantly composed of whitespace or empty spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IERC
    -0.85
    脚注の使い方
    -0.83
     SignIn
    -0.82
    mybatisplus
    -0.80
     مشين
    -0.77
     JPanel
    -0.74
    arraycopy
    -0.73
    ResponseStatus
    -0.73
     Lynx
    -0.73
    Tazama
    -0.72
    POSITIVE LOGITS
                                   
    1.75
                                 
    1.10
                                  
    1.00
                               
    0.99
                         
    0.97
                              
    0.96
                     
    0.95
                                
    0.95
                             
    0.94
                          
    0.92
    Activations Density 0.035%

    No Known Activations