© 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. 1703
    Prev
    Next
    INDEX
    Explanations

    terms related to international law and software licensing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     المعيارى
    -0.79
    __(/*!
    -0.71
    stdafx
    -0.68
    ----</
    -0.67
     beginnetje
    -0.67
    Халык
    -0.64
     cherchés
    -0.63
    nvarchar
    -0.62
     '{@
    -0.61
    rouvez
    -0.60
    POSITIVE LOGITS
     autorytatywna
    0.58
    Cyfeiriadau
    0.49
    jsonwebtoken
    0.47
    IContainer
    0.46
     tombe
    0.45
    ClientSize
    0.43
    gio
    0.42
    SourceChecksum
    0.42
     grig
    0.41
     Kalamazoo
    0.40
    Activations Density 0.099%

    No Known Activations