© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8573
    Prev
    Next
    INDEX
    Explanations

    code structure elements and types used in programming languages

    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
     const
    -0.50
    :✨
    -0.50
    var
    -0.47
     ligiloj
    -0.47
     تانيه
    -0.45
    setupUi
    -0.44
    const
    -0.44
     var
    -0.43
     VAR
    -0.42
    nestjs
    -0.41
    POSITIVE LOGITS
    Datuak
    0.67
    IsContent
    0.57
     zijne
    0.53
    uttosto
    0.52
    klere
    0.49
    WireFormatLite
    0.49
     zelve
    0.47
    matchCondition
    0.45
     transfieras
    0.44
     zichzelf
    0.43
    Activations Density 0.175%

    No Known Activations