© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1252
    Prev
    Next
    INDEX
    Explanations

    XML-related elements and keywords, indicating a focus on XML document structure and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.94
     تضيفلها
    -0.82
    mobileqq
    -0.81
    enterOuterAlt
    -0.77
    UNDP
    -0.73
     Brant
    -0.73
    endphp
    -0.73
     Lillian
    -0.73
     QH
    -0.72
     tas
    -0.72
    POSITIVE LOGITS
     xml
    1.52
    xml
    1.42
     XML
    1.42
     Xml
    1.33
    Xml
    1.29
    XML
    1.21
    xmlhttp
    0.82
    XMLSchema
    0.81
    XmlNode
    0.80
     Buddhist
    0.67
    Activations Density 0.185%

    No Known Activations