© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 4350
    Prev
    Next
    INDEX
    Explanations

    sections of code or documentation that are structured or formatted in a specific way, particularly comments or documentation blocks

    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
     -
    -0.57
     $-
    -0.56
     −
    -0.56
     =-
    -0.53
    ">—
    -0.53
     –
    -0.52
     partita
    -0.50
     -(
    -0.48
    cdot
    -0.48
     lesión
    -0.47
    POSITIVE LOGITS
    ########.
    0.72
     وتسجيلات
    0.71
     AssemblyCompany
    0.70
    CloseOperation
    0.69
     pinulongan
    0.69
     متعلقه
    0.68
     **/
    
    0.68
    URLException
    0.67
    ****************
    0.67
    ंदीखरीदारी
    0.64
    Activations Density 0.195%

    No Known Activations