© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 22822
    Prev
    Next
    INDEX
    Explanations

    the summary sections in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    <eos>
    -0.32
     fallu
    -0.29
     ekor
    -0.29
     payé
    -0.28
      
    -0.27
    Book
    -0.26
    seiti
    -0.26
     
    
    -0.26
     mármol
    -0.26
     espejos
    -0.26
    POSITIVE LOGITS
     kasarigan
    0.98
    ViewFeatures
    0.93
    Personendaten
    0.87
    AccessorTable
    0.86
     esternos
    0.85
     Roskov
    0.83
     nahilalakip
    0.82
    summary
    0.82
     ویکی‌آمباردا
    0.81
    
    0.79
    Activations Density 0.000%

    No Known Activations