© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4521
    Prev
    Next
    INDEX
    Explanations

    terms associated with testing, experimentation, and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    didSet
    -0.61
    ėtų
    -0.52
    ResumeLayout
    -0.49
    initComponents
    -0.47
    ILayout
    -0.47
    ServletException
    -0.47
    LayoutPanel
    -0.47
     капу
    -0.46
     vitae
    -0.46
     Gogh
    -0.46
    POSITIVE LOGITS
     testing
    1.14
     tests
    1.09
     Testing
    1.06
     Tests
    1.03
     test
    0.99
    ControllerTest
    0.98
    Testing
    0.97
     testers
    0.96
     tester
    0.94
    Tests
    0.94
    Activations Density 0.320%

    No Known Activations