© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105277
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases indicative of conclusions, findings, or evaluations in a research or legal context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Negative Logits
    <h1>
    -0.52
    <strong>
    -0.47
    The
    -0.46
    <
    -0.45
    <h2>
    -0.43
    #
    -0.42
    <em>
    -0.41
    On
    -0.41
    1
    -0.39
    “
    -0.39
    POSITIVE LOGITS
    ValueStyle
    1.05
    IUrlHelper
    1.02
     يتيمه
    0.90
    AccessorTable
    0.85
    BufferException
    0.85
    ItemBackground
    0.84
     NSCoder
    0.83
    EndContext
    0.81
    PerformLayout
    0.81
    SequentialGroup
    0.81
    Activations Density 0.101%

    No Known Activations