© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105777
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements and language terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    -0.82
     ſind
    -0.67
     pageIndex
    -0.64
     userSchema
    -0.64
    UPAC
    -0.63
     EconPapers
    -0.63
    
    -0.62
     requestId
    -0.62
     verſ
    -0.61
     iſt
    -0.60
    POSITIVE LOGITS
      
    0.52
       
    0.49
    < 
    0.49
    – 
    0.49
     لل
    0.48
         
    0.47
    + 
    0.47
     ذ
    0.46
    finish
    0.46
     περί
    0.44
    Activations Density 0.001%

    No Known Activations