© 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. 31-GEMMASCOPE-RES-16K
    11. 15175
    Prev
    Next
    INDEX
    Explanations

    content related to blood and bodily fluids

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

    graphic descriptions of bodily fluids and messy situations, particularly involving blood, poop, and sexual fluids.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    This neuron detects descriptions of bodily fluids and messy, graphic content involving blood, waste, or sexual fluids.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     deleteById
    -0.39
    DrawerToggle
    -0.38
     ushort
    -0.34
    StringTokenizer
    -0.33
    hasMoreElements
    -0.33
     '\\;'
    -0.32
     imageNamed
    -0.32
    initComponents
    -0.31
    ICOM
    -0.30
     prosty
    -0.30
    POSITIVE LOGITS
     spilled
    1.13
     spills
    1.05
     splat
    1.03
     spill
    1.02
     spillage
    1.02
     splashes
    1.01
     spilling
    0.99
     splashed
    0.98
     messy
    0.95
     stains
    0.91
    Activations Density 0.306%

    No Known Activations