© 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. 5873
    Prev
    Next
    INDEX
    Explanations

    references to statements or communications from individuals or organizations

    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
     sneaky
    -0.57
     newbies
    -0.56
     sne
    -0.51
     shoved
    -0.50
     newbie
    -0.48
     shoving
    -0.48
     nifty
    -0.47
    偷偷
    -0.47
     wacky
    -0.47
     theoretically
    -0.47
    POSITIVE LOGITS
     regrettable
    0.70
    Regret
    0.69
     Regret
    0.60
     appropriate
    0.59
     discussions
    0.58
    appropriate
    0.57
     regret
    0.57
     communicated
    0.56
    引き続き
    0.56
     circonstances
    0.54
    Activations Density 0.516%

    No Known Activations