© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 72707
    Prev
    Next
    INDEX
    Explanations

    phrases related to objectives and purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     pinulongan
    -0.87
    invokeLater
    -0.72
     ModelExpression
    -0.70
     BrowserModule
    -0.68
     initComponents
    -0.66
     ویکی‌پدیا
    -0.65
    ChildScrollView
    -0.63
    msgTypes
    -0.62
    PerformLayout
    -0.61
    ResumeLayout
    -0.59
    POSITIVE LOGITS
     aimed
    0.48
    是为了
    0.46
     aim
    0.45
     aims
    0.42
     aiming
    0.41
     intended
    0.40
     intention
    0.37
     Absicht
    0.37
     purpose
    0.36
     prevent
    0.36
    Activations Density 0.013%

    No Known Activations