© 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. 1298
    Prev
    Next
    INDEX
    Explanations

    sequences of repeated characters or placeholder text formatting

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

    column definitions and quantities

    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
     $_"
    -0.77
    évaluateur
    -0.75
     queſta
    -0.74
     OFDb
    -0.71
    Autoritní
    -0.70
     eventName
    -0.70
     lateinit
    -0.70
    ]")]
    -0.69
    %)$
    -0.69
     ""}
    -0.69
    POSITIVE LOGITS
                      
    1.27
                       
    1.04
                        
    1.01
    1.01
                     
    0.99
    0.96
                         
    0.93
                          
    0.92
                    
    0.90
                  
    0.87
    Activations Density 0.029%

    No Known Activations