© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 15707
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to theft, especially involving greed and stolen items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttino
    -0.42
    richTextPanel
    -0.40
    EndTag
    -0.38
    TabIndex
    -0.38
    quiagem
    -0.37
    LayoutStyle
    -0.37
    ícil
    -0.37
     setOpen
    -0.37
    cuencia
    -0.37
    blurRadius
    -0.36
    POSITIVE LOGITS
     treasure
    0.67
    treasure
    0.62
    Treasure
    0.62
     loot
    0.60
     Treasure
    0.59
    AndEndTag
    0.59
     plunder
    0.59
    verwijspagina
    0.56
     covet
    0.56
    stolen
    0.55
    Activations Density 0.600%

    No Known Activations