© 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. 41-GEMMASCOPE-RES-16K
    11. 4343
    Prev
    Next
    INDEX
    Explanations

    numerical data and information related to statistics or measurements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     NSCoder
    -0.51
     DialogInterface
    -0.51
    sidemargin
    -0.50
    yntaxException
    -0.49
    omed
    -0.49
    ricing
    -0.48
     taxi
    -0.47
     Tacoma
    -0.47
    脚注の使い方
    -0.46
     boxers
    -0.46
    POSITIVE LOGITS
    August
    0.53
    ⑧
    0.49
     August
    0.47
    八月
    0.46
    Aug
    0.45
    8
    0.45
     августа
    0.43
     agosto
    0.43
    AUGUST
    0.43
     Aug
    0.43
    Activations Density 0.212%

    No Known Activations