© 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. 20-GEMMASCOPE-RES-16K
    11. 15533
    Prev
    Next
    INDEX
    Explanations

    technical terms and mathematical symbols related to scientific concepts

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

    formatting and typographical elements in academic or scientific documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    NameInMap
    -0.66
    WriteTagHelper
    -0.57
     Taktlose
    -0.56
    formik
    -0.54
    yarnpkg
    -0.53
     ſeine
    -0.52
    BibitemShut
    -0.52
     laſſen
    -0.52
     mijne
    -0.51
    tagHelperRunner
    -0.51
    POSITIVE LOGITS
    ⓧ
    0.35
    édrale
    0.35
     finne
    0.34
    UTF
    0.33
     '{@
    0.31
    fuhr
    0.29
    <bos>
    0.28
    AV
    0.28
     LOV
    0.28
    ITTLE
    0.27
    Activations Density 0.399%

    No Known Activations