© 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. 33-GEMMASCOPE-RES-16K
    11. 7899
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS structure, as well as JavaScript elements and behaviors within web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.82
    ftagPool
    -0.66
    ьаж
    -0.63
     kasarigan
    -0.61
    findpost
    -0.60
     Normdatei
    -0.60
     Meksiku
    -0.58
    الحياه
    -0.58
    rungsseite
    -0.57
    mdb
    -0.57
    POSITIVE LOGITS
    clearfix
    0.36
     pensato
    0.36
    span
    0.31
     Sinclair
    0.31
    arschijnlijk
    0.28
     хватает
    0.26
     suspensión
    0.26
     olduğunu
    0.25
     Clearly
    0.25
    ul
    0.25
    Activations Density 0.248%

    No Known Activations