© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 72731
    Prev
    Next
    INDEX
    Explanations

    temporal adverbs indicating time references in the text

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

    earlier or later time references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.50
     contacts
    -0.48
    Kanpo
    -0.47
     Contacts
    -0.47
    readFileSync
    -0.45
    nisses
    -0.45
    Panamoan
    -0.44
     åt
    -0.44
    Contacts
    -0.43
    つもり
    -0.43
    POSITIVE LOGITS
     today
    0.46
     month
    0.45
     tonight
    0.44
     year
    0.43
    semana
    0.43
     kasarigan
    0.42
     semaine
    0.40
     week
    0.39
     hoje
    0.38
     semester
    0.37
    Activations Density 0.008%

    No Known Activations