© 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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 22286
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and commas, indicating sentence and clause boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gand
    -0.59
    usha
    -0.55
     LAMB
    -0.52
     chio
    -0.51
    tienne
    -0.51
     Nickel
    -0.50
     flott
    -0.49
     iyon
    -0.48
     utafitiHapana
    -0.48
     surla
    -0.48
    POSITIVE LOGITS
    ")]
    
    0.81
    '))
    
    0.80
    ()]
    
    0.79
    '],$
    0.79
    )++;
    0.74
    "]}
    0.74
     '))
    0.73
     ')
    
    0.73
     colorWith
    0.73
    )))
    
    0.72
    Activations Density 0.003%

    No Known Activations