© 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. 21-GEMMASCOPE-RES-16K
    11. 13320
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax and structure in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Actividades
    -0.37
    hå
    -0.36
     activity
    -0.36
     balanced
    -0.36
     uzyskać
    -0.35
     särsk
    -0.35
     skrift
    -0.35
     incluido
    -0.35
     activities
    -0.35
     sold
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    0.87
    TagMode
    0.83
     betweenstory
    0.81
    ConstraintMaker
    0.77
     propOrder
    0.77
     estekak
    0.77
    postIndex
    0.76
    IUrlHelper
    0.76
     autorytatywna
    0.75
    SharedDtor
    0.75
    Activations Density 0.065%

    No Known Activations