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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3577
    Prev
    Next
    INDEX
    Explanations

    phrases related to understanding and explaining details or complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Източници
    -0.59
    UnusedPrivate
    -0.54
    MigrationBuilder
    -0.48
    GTCX
    -0.48
    webElement
    -0.47
    webElementXpaths
    -0.46
    脚注の使い方
    -0.44
    exels
    -0.44
    ChildScrollView
    -0.42
     feit
    -0.42
    POSITIVE LOGITS
     intricacies
    0.96
     implications
    0.90
     meaning
    0.89
     origins
    0.86
     exact
    0.85
     specifics
    0.84
     details
    0.83
     significance
    0.82
     particulars
    0.79
     basics
    0.78
    Activations Density 0.719%

    No Known Activations