© 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 - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3270
    Prev
    Next
    INDEX
    Explanations

    code annotations related to methods and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unfinished
    -0.95
    graphicx
    -0.59
    core
    -0.49
     unfinished
    -0.44
     component
    -0.36
     Kompon
    -0.35
    addComponent
    -0.35
     COMPONENT
    -0.34
    component
    -0.34
    finished
    -0.33
    POSITIVE LOGITS
    :][
    3.06
    ScopeManager
    2.67
    ValueStyle
    1.73
    ArgsConstructor
    1.70
    addGap
    1.28
    addCriterion
    1.12
    IsContent
    1.07
    addPreferredGap
    1.07
    makeText
    1.02
    ftagPool
    1.02
    Activations Density 0.002%

    No Known Activations