© 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. 28-GEMMASCOPE-RES-16K
    11. 8735
    Prev
    Next
    INDEX
    Explanations

    numerical values or mentions of quantities related to financial revenues and legal actions

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

    Followed by "in" or a punctuation mark

    np_acts-logits-general · gemini-2.0-flash

    past actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     today
    -0.92
     recently
    -0.88
     recent
    -0.86
     nowadays
    -0.83
     dziś
    -0.81
     lately
    -0.79
     aujourd
    -0.78
     recentemente
    -0.78
     recientemente
    -0.77
     earlier
    -0.77
    POSITIVE LOGITS
    GEBURTS
    0.63
    queryInterface
    0.54
    bewerken
    0.52
     queſto
    0.52
     الرياضيه
    0.52
    Билгалдахарш
    0.51
    encodeWith
    0.50
    ercises
    0.50
    
    0.49
    QRST
    0.49
    Activations Density 1.008%

    No Known Activations