© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10647
    Prev
    Next
    INDEX
    Explanations

    high activation levels related to specific coding conventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.69
    fromCharCode
    -0.55
     ddelwed
    -0.55
     indígen
    -0.53
    sizeCache
    -0.52
     detuvo
    -0.52
    SharedCtor
    -0.51
    исленность
    -0.51
    SourceChecksum
    -0.51
    хьтан
    -0.51
    POSITIVE LOGITS
     AssemblyTitle
    0.52
    __(/*!
    0.52
     []:
    0.51
     cref
    0.51
    KommentareTeilen
    0.47
    matchCondition
    0.44
     <<<<<<<<<<<<<<
    0.43
    numerusform
    0.42
     متعلقه
    0.38
    subsubsection
    0.35
    Activations Density 0.035%

    No Known Activations