© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 7144
    Prev
    Next
    INDEX
    Explanations

    mentions of time-related concepts, specifically the word "year" and sequences/numbers related to rounds in tournaments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gynhyrchwyd
    -0.32
    kitan
    -0.28
     Lawrence
    -0.28
     Aitken
    -0.28
     rojo
    -0.28
    RefreshLayout
    -0.28
     Gers
    -0.28
     Becken
    -0.27
    charpe
    -0.27
     roja
    -0.27
    POSITIVE LOGITS
     round
    3.84
     Round
    3.42
    round
    3.33
    Round
    3.30
     ROUND
    3.23
     rounds
    2.91
    ROUND
    2.88
     Rounds
    2.66
     rounded
    2.55
     rounding
    2.55
    Activations Density 0.526%

    No Known Activations