© 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. 9-GEMMASCOPE-RES-131K
    11. 27950
    Prev
    Next
    INDEX
    Explanations

    phrases related to activities or events occurring late at night

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

    late hours and long durations

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     cucchiaio
    -0.34
     próxima
    -0.32
     apă
    -0.31
    Lugares
    -0.31
    mbangkan
    -0.30
     AppCompatTheme
    -0.30
     suç
    -0.30
     rodea
    -0.30
     aarde
    -0.30
     invloed
    -0.30
    POSITIVE LOGITS
     للاسماء
    0.77
     utafitiHapana
    0.75
    StructEnd
    0.73
     kasarigan
    0.72
    WebElementEntity
    0.72
     hours
    0.68
    hours
    0.68
     midnight
    0.66
     nights
    0.66
    midnight
    0.66
    Activations Density 0.139%

    No Known Activations