© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 11503
    Prev
    Next
    INDEX
    Explanations

    phrases indicating changes or transitions over time

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

    [Something] was, but now [something else]

    np_acts-logits-general · gemini-2.0-flash

    past versus now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.54
     Paglinawan
    -0.52
    Хьажоргаш
    -0.51
    SharedDtor
    -0.49
    krok
    -0.48
     bParam
    -0.47
    Чыганаклар
    -0.47
    twimg
    -0.47
    scryfall
    -0.44
    noch
    -0.43
    POSITIVE LOGITS
     now
    0.98
     ahora
    0.77
     agora
    0.68
     теперь
    0.68
     sekarang
    0.67
     nyní
    0.67
     teď
    0.65
     teraz
    0.64
    今では
    0.63
    now
    0.62
    Activations Density 0.365%

    No Known Activations