© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5424
    Prev
    Next
    INDEX
    Explanations

    references to file handling and AJAX functionalities in programming

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

    technical code and programming-related tokens, especially related to web development and file handling.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.73
    WithIOException
    -0.71
    __":
    -0.68
    Autoritní
    -0.67
    SharedDtor
    -0.65
    ----</
    -0.63
    >{@
    -0.62
    <unused40>
    -0.60
    <unused23>
    -0.60
    <unused8>
    -0.60
    POSITIVE LOGITS
    ajax
    0.40
     JsonResult
    0.38
    Ajax
    0.36
    Discover
    0.32
     JsonResponse
    0.32
    RotationOrder
    0.32
     dAtA
    0.32
    JSON
    0.31
     Discovery
    0.31
     fe
    0.31
    Activations Density 0.059%

    No Known Activations