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

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 15616
    Prev
    Next
    INDEX
    Explanations

    specific references to authority or significant figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
    PreferredItem
    -0.55
     betweenstory
    -0.51
    الإنجليزية
    -0.50
     '\\;'
    -0.46
    delwed
    -0.44
     række
    -0.43
     voks
    -0.42
     måde
    -0.41
    EXIST
    -0.41
     abstra
    -0.41
    POSITIVE LOGITS
    Geplaatst
    0.54
    دانشنامهٔ
    0.45
     fieldNum
    0.41
    AntiForgeryToken
    0.41
    transQ
    0.40
    したもの
    0.40
     Réponses
    0.39
     Wikipédia
    0.39
    なもの
    0.39
     Eintrag
    0.37
    Activations Density 1.512%

    No Known Activations