© 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. 22-GEMMASCOPE-RES-16K
    11. 6094
    Prev
    Next
    INDEX
    Explanations

    questions and requests for information or clarification

    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
     كومونز
    -0.48
    pholes
    -0.46
    mappedBy
    -0.45
     onData
    -0.40
     iNdEx
    -0.40
     beginnetje
    -0.38
     gevolg
    -0.37
    等你
    -0.37
     Aggregate
    -0.37
    cipital
    -0.36
    POSITIVE LOGITS
     please
    0.85
    please
    0.69
     PLEASE
    0.65
     Please
    0.60
    Please
    0.60
     пожалуйста
    0.56
    PLEASE
    0.52
     pls
    0.52
     plz
    0.51
     Paglinawan
    0.51
    Activations Density 0.312%

    No Known Activations