© 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 - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 10265
    Prev
    Next
    INDEX
    Explanations

    patterns related to object properties in code, specifically those that follow a dot notation structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -0.71
     pinulongan
    -0.70
    ErrUnexpectedEOF
    -0.66
    VIAF
    -0.65
    ::__
    -0.63
    &__
    -0.63
     متعلقه
    -0.63
     (!__
    -0.62
    WithIOException
    -0.61
    parsedMessage
    -0.59
    POSITIVE LOGITS
    ._
    1.33
    ftagPool
    0.66
    ]._
    0.64
    )._
    0.61
    piller
    0.56
     AssemblyProduct
    0.56
    endregion
    0.56
    AddColumn
    0.54
     Piedmont
    0.54
    endish
    0.53
    Activations Density 0.080%

    No Known Activations