© 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. 24584
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references in a structured context

    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
    windowFixed
    -0.69
     Мексичка
    -0.57
     Exactos
    -0.57
    Ӕ
    -0.56
     nahilalakip
    -0.52
     mxArray
    -0.51
     للمعارف
    -0.51
    Tikang
    -0.50
    !")
    
    -0.50
     referenties
    -0.50
    POSITIVE LOGITS
     leder
    0.40
     formales
    0.35
    UseVisualStyle
    0.35
    insegna
    0.34
    mainAxisSize
    0.34
    
    0.33
    iyle
    0.33
     Zjednoc
    0.33
     formal
    0.32
    formal
    0.32
    Activations Density 0.249%

    No Known Activations