© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 797
    Prev
    Next
    INDEX
    Explanations

    references to upcoming events and important dates

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

    specific dates and events, particularly future events or announcements.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    libft
    -0.59
     createSlice
    -0.56
    Autoritní
    -0.56
     Wikimedijinoj
    -0.54
    stylers
    -0.51
     transférez
    -0.49
    getActiveSheet
    -0.49
     الرياضيه
    -0.48
    twimg
    -0.48
     חיצוניים
    -0.48
    POSITIVE LOGITS
     tomorrow
    0.76
     upcoming
    0.59
    Tomorrow
    0.59
    tomorrow
    0.58
     prossima
    0.57
     prossimo
    0.56
    morrow
    0.55
     prochain
    0.54
     demain
    0.49
     Tomorrow
    0.48
    Activations Density 0.212%

    No Known Activations