© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 37976
    Prev
    Next
    INDEX
    Explanations

    references to memorials and victims of historical tragedies

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

    died, loss of life, casualties

    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
    OGND
    -0.62
    SharedDtor
    -0.60
     kasarigan
    -0.57
    الحياه
    -0.56
     informée
    -0.54
    IntoConstraints
    -0.54
     propOrder
    -0.54
     lenker
    -0.53
    WebServlet
    -0.51
     ब्रेकडाउन
    -0.51
    POSITIVE LOGITS
     victims
    0.99
     deceased
    0.96
     perished
    0.91
     victimes
    0.86
     casualties
    0.85
     died
    0.85
     killed
    0.84
     zmar
    0.84
     lost
    0.83
     Victims
    0.83
    Activations Density 0.043%

    No Known Activations