© 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. 28-GEMMASCOPE-RES-16K
    11. 6342
    Prev
    Next
    INDEX
    Explanations

    events or activities related to travel and tourism

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

    "Week" or time period references

    np_acts-logits-general · gemini-2.0-flash

    week, weeks, month, days

    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
    Year
    -0.67
    Yearly
    -0.66
     Year
    -0.65
     YEAR
    -0.65
     year
    -0.64
     Италијани
    -0.64
    yearly
    -0.63
    year
    -0.62
     Yearly
    -0.61
    YEAR
    -0.59
    POSITIVE LOGITS
     week
    1.62
     Week
    1.37
    week
    1.34
    Week
    1.34
     weeks
    1.29
     WEEK
    1.26
     semana
    1.16
    WEEK
    1.11
     Woche
    1.09
    weeks
    1.09
    Activations Density 0.524%

    No Known Activations