© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2573
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to descriptions of materials and their properties

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

    when clauses

    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
    makeConstraints
    -0.66
    はじめに
    -0.59
     насељу
    -0.59
    ьаж
    -0.57
    sumowanie
    -0.56
     defaultstate
    -0.54
    Pyx
    -0.51
     intptr
    -0.51
    InjectMocks
    -0.51
    ضايا
    -0.50
    POSITIVE LOGITS
     when
    2.23
    when
    1.95
     quando
    1.71
     cuando
    1.67
     WHEN
    1.60
    When
    1.52
     lorsqu
    1.51
     When
    1.48
     когда
    1.42
    cuando
    1.40
    Activations Density 0.521%

    No Known Activations