© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8400
    Prev
    Next
    INDEX
    Explanations

    elements related to tabular data structures or formatting

    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
    ModelForm
    -0.37
    DECREF
    -0.35
     cuenca
    -0.35
     item
    -0.34
    Pages
    -0.33
     foes
    -0.33
     HttpNotFound
    -0.32
    StoryboardSegue
    -0.32
    dstuk
    -0.32
     Datenschutzer
    -0.32
    POSITIVE LOGITS
    <tbody>
    0.80
    <thead>
    0.69
     ſmall
    0.60
    <caption>
    0.59
     themſelves
    0.57
     Theſe
    0.56
     myſelf
    0.55
     ſeveral
    0.53
    Tembelea
    0.52
     leſs
    0.52
    Activations Density 0.070%

    No Known Activations