© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3769
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    web development code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Geplaatst
    -0.88
    RegressionTest
    -0.83
    openzeppelin
    -0.82
    ftagPool
    -0.81
     Италијани
    -0.80
     مُعرِّف
    -0.79
    <bos>
    -0.78
    OGND
    -0.78
     Paglinawan
    -0.78
    Билгалдахарш
    -0.75
    POSITIVE LOGITS
     useRouter
    0.50
    udio
    0.47
     useParams
    0.46
     ď
    0.44
    FormTagHelper
    0.43
    </b>
    0.41
     useHistory
    0.40
    Finalize
    0.39
    </td>
    0.39
    writeFieldEnd
    0.39
    Activations Density 0.089%

    No Known Activations