© 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. 40-GEMMASCOPE-RES-16K
    11. 6334
    Prev
    Next
    INDEX
    Explanations

    references to offensive content and warnings about it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.44
     رع
    -0.40
    ⋱
    -0.39
    EndGlobal
    -0.37
     Paglinawan
    -0.37
     مهر
    -0.35
    rumah
    -0.35
    новниш
    -0.35
    withOpacity
    -0.35
     Winaray
    -0.35
    POSITIVE LOGITS
     offensive
    1.19
     nudity
    1.04
     objectionable
    1.03
     Offensive
    1.00
     vulgar
    0.99
     NSFW
    0.97
     explicit
    0.97
    Offensive
    0.97
    offensive
    0.96
     obscene
    0.96
    Activations Density 0.571%

    No Known Activations