© 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. 105752
    Prev
    Next
    INDEX
    Explanations

    concepts related to the potential applications and benefits of scientific discoveries or medical strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    health benefits and clinical applications

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     propOrder
    -0.71
    WriteTagHelper
    -0.64
     IBOutlet
    -0.63
     iprot
    -0.62
     surla
    -0.60
     CreateTagHelper
    -0.60
    ьаж
    -0.60
    iſen
    -0.59
    sizeCache
    -0.59
    principalColumn
    -0.59
    POSITIVE LOGITS
    endpush
    0.42
    <eos>
    0.35
     pungkas
    0.33
     offres
    0.32
     muhimu
    0.30
    appBar
    0.29
    graphicx
    0.29
    或许
    0.28
     poate
    0.28
     novel
    0.28
    Activations Density 0.138%

    No Known Activations