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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 100112
    Prev
    Next
    INDEX
    Explanations

    references to burial sites and monuments

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

    tombs and graves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    はじめに
    -0.58
     Prim
    -0.58
     Ener
    -0.57
    Fraser
    -0.57
    Indians
    -0.57
    Matter
    -0.57
    Matters
    -0.57
     Indians
    -0.55
     Nelly
    -0.55
    racha
    -0.54
    POSITIVE LOGITS
     tomb
    0.83
     tombs
    0.68
     tumba
    0.66
    Tomb
    0.66
     Tomb
    0.65
     tombstone
    0.60
     cemetery
    0.58
    tomb
    0.52
     моги
    0.50
     coffin
    0.49
    Activations Density 0.006%

    No Known Activations