© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 10079
    Prev
    Next
    INDEX
    Explanations

    references to historical events and significant figures with an emphasis on conflict and tragedy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.48
    MessageState
    -0.44
    Rüyada
    -0.40
     tartalomajánló
    -0.38
    PageRoute
    -0.38
    StructEnd
    -0.37
     ostavi
    -0.36
    Vanjske
    -0.35
    KommentareTeilen
    -0.35
    ageo
    -0.35
    POSITIVE LOGITS
     WWII
    1.12
     WWI
    1.05
     WW
    1.02
     Chernobyl
    1.00
     World
    0.97
     Hiroshima
    0.96
    WW
    0.93
     Hitler
    0.93
     Vietnam
    0.86
     Nazi
    0.84
    Activations Density 1.012%

    No Known Activations