© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 7444
    Prev
    Next
    INDEX
    Explanations

    references to property damage and maintenance issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orsese
    -0.51
    igné
    -0.49
     <>",
    -0.48
    BeginContext
    -0.47
     Canto
    -0.44
    +#+
    -0.44
    FromArgb
    -0.43
    epam
    -0.43
    structors
    -0.42
    HandlerContext
    -0.42
    POSITIVE LOGITS
     windows
    1.05
     window
    0.97
     refrigerator
    0.96
     faucets
    0.94
     curtains
    0.92
     faucet
    0.91
     stove
    0.91
     fridge
    0.89
     blinds
    0.86
     sink
    0.86
    Activations Density 0.364%

    No Known Activations