© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8132
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change or trend over time

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

    time, like "lately" or "years."

    np_acts-logits-general · gemini-2.0-flash

    recent past

    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
    elesaikan
    -0.35
     still
    -0.34
     Almanac
    -0.33
     fortsatt
    -0.32
     videre
    -0.32
     original
    -0.32
     verfü
    -0.31
     Reiche
    -0.31
     навсегда
    -0.31
    Cuántos
    -0.31
    POSITIVE LOGITS
     Lately
    1.11
     lately
    1.09
    Recent
    1.06
     recent
    1.04
    recent
    1.02
     recente
    0.98
     Recent
    0.97
    Recently
    0.94
     RECENT
    0.90
    recently
    0.90
    Activations Density 0.322%

    No Known Activations