© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4317
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and news broadcasting

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

    time duration

    np_acts-logits-general · gemini-2.0-flash

    round the clock

    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
    InputTagHelper
    -0.47
    Date
    -0.35
    plaat
    -0.35
    Future
    -0.34
    XmlType
    -0.34
    }{#
    -0.33
     tane
    -0.32
     FUTURE
    -0.32
     gari
    -0.32
    ematica
    -0.31
    POSITIVE LOGITS
     nonstop
    0.79
    ตลอด
    0.75
     continuously
    0.71
     continuous
    0.71
    contin
    0.69
     Anytime
    0.68
     anytime
    0.68
     CONTIN
    0.67
    Anytime
    0.66
     uninterrupted
    0.66
    Activations Density 0.156%

    No Known Activations