© 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. 30-GEMMASCOPE-RES-16K
    11. 10849
    Prev
    Next
    INDEX
    Explanations

    phrases indicating temporal context or timing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mentions the time something occurred

    np_acts-logits-general · gemini-2.0-flash

    writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fras
    -0.37
    GEBURTSDATUM
    -0.32
    Motiv
    -0.30
     tul
    -0.30
    verifyException
    -0.29
     PDS
    -0.29
     raste
    -0.28
     FS
    -0.28
     تور
    -0.28
    setIsLoading
    -0.28
    POSITIVE LOGITS
     writing
    1.45
    writing
    1.22
     Writing
    1.18
     write
    1.17
    Writing
    1.16
     WRITING
    1.14
    WRITING
    1.10
    write
    1.06
     Write
    1.02
     escribir
    1.00
    Activations Density 0.176%

    No Known Activations