Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14109
    Prev
    Next
    INDEX
    Explanations

    code structures related to XML document creation and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insegna
    -0.66
    SharedCtor
    -0.66
    دانشنامهٔ
    -0.60
     GenerationType
    -0.56
    tembro
    -0.54
     Townsend
    -0.52
     Wiesbaden
    -0.52
     га
    -0.52
    RefNanny
    -0.52
     CUDA
    -0.52
    POSITIVE LOGITS
     XML
    1.21
     xml
    1.18
    xml
    1.06
    XML
    1.04
     Xml
    0.98
    Xml
    0.94
    XmlAttribute
    0.79
     xm
    0.72
    XmlNode
    0.72
    SAX
    0.71
    Activations Density 0.503%

    No Known Activations