© 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. 2-GEMMASCOPE-RES-16K
    11. 493
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement or admiration, particularly the word "awesome."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    rungsseite
    -0.58
    complexContent
    -0.53
    CppMethod
    -0.51
    Gön
    -0.49
     JpaRepository
    -0.47
     avoiding
    -0.47
     HFILL
    -0.46
    Dichloropropene
    -0.46
    ClientSize
    -0.45
    sizeCache
    -0.45
    POSITIVE LOGITS
    @
    0.68
    Awesome
    0.65
     Awesome
    0.57
     Ok
    0.52
    Ok
    0.50
     Chriftian
    0.50
    Okay
    0.50
     awesome
    0.48
     Majefty
    0.47
    ActionPerformed
    0.46
    Activations Density 0.101%

    No Known Activations