© 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. 36-GEMMASCOPE-RES-16K
    11. 14995
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS elements related to web page structure and styling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.81
    ロウィン
    -0.75
    expandindo
    -0.72
    UrlResolution
    -0.71
    Tikang
    -0.70
     noDo
    -0.70
    Manbalar
    -0.70
    OGND
    -0.68
    EDEFAULT
    -0.67
    цездатний
    -0.67
    POSITIVE LOGITS
    glyphicon
    0.38
     enctype
    0.35
     onSubmit
    0.33
     major
    0.32
    </
    0.30
     rat
    0.30
     mysqli
    0.30
     child
    0.30
     he
    0.30
    align
    0.30
    Activations Density 0.210%

    No Known Activations