© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10587
    Prev
    Next
    INDEX
    Explanations

    the Japanese word "を" and variations of the word "whom"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.40
            
    -0.38
     compositeur
    -0.38
              
    -0.34
    nF
    -0.33
     events
    -0.33
    }{||
    -0.33
    UNUSED
    -0.33
             
    -0.32
     czł
    -0.32
    POSITIVE LOGITS
    devamını
    0.79
    folios
    0.61
    日を
    0.60
     ואת
    0.60
    名を
    0.60
    ThroughAttribute
    0.58
    ğunu
    0.58
    気を
    0.57
    ceğini
    0.57
     를
    0.56
    Activations Density 0.077%

    No Known Activations