© 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. 33-GEMMASCOPE-RES-16K
    11. 4800
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "being on track" or "being on a path."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     typelib
    -0.49
    RegressionTest
    -0.47
    Diweddarwch
    -0.45
    strijden
    -0.44
    gaande
    -0.42
    ViewFeatures
    -0.42
     AssemblyCulture
    -0.41
    めでとう
    -0.41
    errHandler
    -0.41
     للمعارف
    -0.41
    POSITIVE LOGITS
     verge
    0.57
     mission
    0.54
     cusp
    0.50
     track
    0.49
     precipice
    0.47
     alert
    0.46
     Mission
    0.45
     MISSION
    0.45
     lookout
    0.44
     target
    0.44
    Activations Density 0.156%

    No Known Activations