© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 1526
    Prev
    Next
    INDEX
    Explanations

    references to code and documentation elements in programming

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

    References/citations, often bracketed with "@" and identifiers

    np_acts-logits-general · gemini-2.0-flash

    latex citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perdido
    -0.29
     agregado
    -0.28
     ancha
    -0.28
    ↵↵
    -0.27
     griega
    -0.26
     pública
    -0.26
     espada
    -0.26
    <h3>
    -0.26
     oculto
    -0.25
     impreso
    -0.25
    POSITIVE LOGITS
    httphttps
    0.96
     surla
    0.88
     cref
    0.85
     }{@
    0.81
    >{@
    0.76
     wireType
    0.75
     للاسماء
    0.75
     '{@
    0.74
    msgTypes
    0.72
    WriteTagHelper
    0.70
    Activations Density 1.888%

    No Known Activations