© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8057
    Prev
    Next
    INDEX
    Explanations

    references to XML and JSON data formats and their related functionalities

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

    "Xml" or "Fm"

    np_acts-logits-general · gemini-2.0-flash

    Xml processing documents

    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
     فريبيس
    -0.61
    EClass
    -0.60
    featureID
    -0.60
    WM
    -0.56
     PAZ
    -0.56
    WL
    -0.54
    QN
    -0.54
    IVA
    -0.53
    WB
    -0.53
    ace
    -0.53
    POSITIVE LOGITS
     anún
    0.56
     desmotivaciones
    0.48
     OFDb
    0.45
     vegetación
    0.44
     receitas
    0.44
     ángeles
    0.44
    horabuena
    0.44
     Infór
    0.44
     coches
    0.44
     víctima
    0.44
    Activations Density 0.602%

    No Known Activations