© 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. 1-GEMMASCOPE-RES-16K
    11. 11392
    Prev
    Next
    INDEX
    Explanations

    the presence of the term "za."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.53
     StatefulWidget
    -0.52
    tagHelperRunner
    -0.52
    MessageOf
    -0.51
     McManus
    -0.49
     صوتيه
    -0.47
    AndEndTag
    -0.45
     shoot
    -0.43
     argint
    -0.43
    AutoScaleMode
    -0.43
    POSITIVE LOGITS
    za
    0.97
    за
    0.92
    ZA
    0.79
    ЗА
    0.66
    За
    0.60
     tight
    0.59
     ЗА
    0.58
    zas
    0.57
     за
    0.54
    ContentLoaded
    0.53
    Activations Density 0.279%

    No Known Activations