© 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. 17387
    Prev
    Next
    INDEX
    Explanations

    biographical details about individuals, including their familial relationships, notable events, and places associated with their lives

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

    death and dates

    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
     &___
    -0.50
     Wiktionnaire
    -0.45
    KELEY
    -0.45
    Enllaços
    -0.44
    mnop
    -0.42
    Kanpo
    -0.40
    jardins
    -0.39
    /*
    -0.38
    íí
    -0.38
     Италијани
    -0.38
    POSITIVE LOGITS
     died
    1.13
     Died
    0.85
    died
    0.81
     murió
    0.80
    Died
    0.78
    Décès
    0.76
     meninggal
    0.75
     morreu
    0.72
     død
    0.70
     death
    0.68
    Activations Density 0.016%

    No Known Activations