© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 126756
    Prev
    Next
    INDEX
    Explanations

    sequences of formatting characters or whitespace in the document

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

    constants assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     queſta
    -1.02
    ésult
    -0.81
     $_"
    -0.79
     faſt
    -0.78
     ainfi
    -0.74
    endphp
    -0.73
    ſelves
    -0.72
     $_(
    -0.72
    évaluateur
    -0.71
    parsedMessage
    -0.71
    POSITIVE LOGITS
                                
    1.47
    1.23
                              
    1.06
                                 
    1.04
                            
    1.02
                               
    1.00
                                  
    0.99
                             
    0.97
    0.94
                        
    0.94
    Activations Density 0.010%

    No Known Activations