© 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. 2890
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and elements in code

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

    programming language syntax elements like colons, types, and function declarations.

    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
     Italijani
    -0.46
    ToAction
    -0.44
    tomans
    -0.44
    GTCX
    -0.44
     BrowserModule
    -0.42
    MessageWindow
    -0.42
    xsi
    -0.40
    Bakgrunnsstoff
    -0.40
    bulin
    -0.39
     FileReader
    -0.39
    POSITIVE LOGITS
    propTypes
    0.58
     propTypes
    0.55
     disambiguazione
    0.54
    CppMethod
    0.50
    PropTypes
    0.44
     ujednoznacz
    0.44
    delijk
    0.43
     vertra
    0.42
     PhpStorm
    0.42
     publiek
    0.41
    Activations Density 0.071%

    No Known Activations