© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101327
    Prev
    Next
    INDEX
    Explanations

    key phrases associated with accomplishments and competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentLoaded
    -0.58
     שוליים
    -0.56
    nonatomic
    -0.56
     كومونز
    -0.54
    -------------</
    -0.54
     >=",
    -0.53
    TestingModule
    -0.52
    StateToProps
    -0.52
    orElseThrow
    -0.52
    BeginInit
    -0.51
    POSITIVE LOGITS
     contestants
    0.38
     pageant
    0.37
     competed
    0.36
     Contest
    0.35
     Wachs
    0.34
    ussch
    0.34
    apkan
    0.33
     audition
    0.33
     contestant
    0.33
    Contest
    0.32
    Activations Density 0.001%

    No Known Activations