© 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. 1694
    Prev
    Next
    INDEX
    Explanations

    notations related to Java persistence and entity management

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

    import and decorators

    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
    TagMode
    -0.74
    новништво
    -0.68
    oyer
    -0.66
     fidé
    -0.65
    InjectAttribute
    -0.64
     nôtre
    -0.63
    曖昧さ回避
    -0.62
    SourceChecksum
    -0.62
     kaynağından
    -0.60
    jednoc
    -0.59
    POSITIVE LOGITS
    @
    0.64
     at
    0.62
    IContainer
    0.57
     Meksiku
    0.56
    import
    0.52
     @
    0.51
     consign
    0.46
     causality
    0.44
    At
    0.43
     sessionFactory
    0.42
    Activations Density 0.008%

    No Known Activations