© 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. 2-GEMMASCOPE-RES-16K
    11. 6192
    Prev
    Next
    INDEX
    Explanations

    references to XML and JSON data formats and their associated syntax or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.45
     estekak
    -0.43
    ArrowToggle
    -0.42
     Hach
    -0.42
     conmigo
    -0.42
     Incident
    -0.41
    thâu
    -0.41
     prove
    -0.40
     víctimas
    -0.40
     WARREN
    -0.40
    POSITIVE LOGITS
     xml
    1.84
     XML
    1.83
    XML
    1.82
    xml
    1.69
    Xml
    1.63
     Xml
    1.43
     json
    1.24
    Json
    1.23
     JSON
    1.13
    JSON
    1.02
    Activations Density 0.093%

    No Known Activations