© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 234
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values or identifiers within a document

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

    structural elements or formatting indicators within the text

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

    polynomials followed by numbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     userSchema
    -0.65
     forhold
    -0.62
     stiefel
    -0.62
    forName
    -0.59
     nucléaire
    -0.59
    égard
    -0.58
    ISupport
    -0.57
    냠
    -0.57
     Inscrivez
    -0.57
    FERENCE
    -0.57
    POSITIVE LOGITS
     CreateTagHelper
    0.77
    RegressionTest
    0.64
     referenties
    0.62
     насељу
    0.62
    ondheim
    0.62
    AddTagHelper
    0.61
    aarrggbb
    0.60
    はじめに
    0.57
    ponses
    0.56
    Autoritní
    0.56
    Activations Density 0.102%

    No Known Activations