© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12191
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to abstract syntax trees (AST)

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

    assertion statements in test code that compare expected values using toBe().

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputStream
    -0.42
    DataContract
    -0.42
     yyr
    -0.38
     BioLib
    -0.38
    PropertyChanging
    -0.37
    DataOutputStream
    -0.37
    QSize
    -0.36
    ensement
    -0.36
    teos
    -0.36
     nonUne
    -0.36
    POSITIVE LOGITS
    expect
    0.52
    describe
    0.47
     expect
    0.46
     describe
    0.45
     mxArray
    0.44
     незавершена
    0.43
    RectangleBorder
    0.43
    quelize
    0.43
     Enzyme
    0.43
     mergeFrom
    0.42
    Activations Density 0.125%

    No Known Activations