© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15038
    Prev
    Next
    INDEX
    Explanations

    references to functions, methods, and data structures within programming or code contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.81
    AndEndTag
    -0.80
    windowFixed
    -0.71
     الحره
    -0.69
     betweenstory
    -0.67
    exitRule
    -0.63
    StoryboardSegue
    -0.61
    ImageContext
    -0.59
     EconPapers
    -0.59
     ddelweddau
    -0.59
    POSITIVE LOGITS
    when
    0.91
     if
    0.90
    if
    0.90
     when
    0.84
    val
    0.81
    require
    0.77
    println
    0.75
     "${
    0.65
    with
    0.65
    "${
    0.64
    Activations Density 0.045%

    No Known Activations