© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5568
    Prev
    Next
    INDEX
    Explanations

    instances of time-related phrases and beginnings of narratives

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

    Triggers on words like "start", "beginning" and similar

    np_acts-logits-general · gemini-2.0-flash

    from the start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actualidad
    -0.47
     derniers
    -0.45
     dernier
    -0.42
     terakhir
    -0.41
     poslední
    -0.40
     habet
    -0.39
     posled
    -0.38
     groet
    -0.38
     letzte
    -0.38
    actualité
    -0.37
    POSITIVE LOGITS
     estekak
    0.70
     сразу
    0.68
     early
    0.67
     immediately
    0.64
    最初から
    0.61
    immediately
    0.59
     Immediately
    0.58
    early
    0.56
    Immediately
    0.56
     subito
    0.56
    Activations Density 0.396%

    No Known Activations