© 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. 38-GEMMASCOPE-RES-16K
    6. 15021
    Prev
    Next
    INDEX
    Explanations

    elements of asynchronous programming and error handling in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.51
     AssemblyTitle
    -0.46
    OrBuilder
    -0.45
    hdashline
    -0.41
     endregion
    -0.40
     Ghi
    -0.38
     "..\..\..\
    -0.38
    úblico
    -0.37
     stands
    -0.37
     καν
    -0.36
    POSITIVE LOGITS
    console
    1.84
     console
    1.70
     let
    1.48
    let
    1.45
    const
    1.34
     const
    1.15
     consoles
    1.10
    setTimeout
    1.02
    Let
    0.91
    debugger
    0.91
    Activations Density 0.225%

    No Known Activations