© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7477
    Prev
    Next
    INDEX
    Explanations

    terms related to blood evidence and stains

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

    blood or stains

    np_acts-logits-general · gemini-2.0-flash

    stains and spills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.43
    vician
    -0.37
    saan
    -0.35
    oneofs
    -0.35
    __()
    -0.33
    رشف
    -0.32
     scatola
    -0.32
     eletrônico
    -0.32
    azgo
    -0.32
    Искәрмәләр
    -0.32
    POSITIVE LOGITS
     stains
    0.73
     spills
    0.69
     Splash
    0.62
     splashes
    0.61
     spilled
    0.60
     spilling
    0.60
     splashed
    0.59
     salpic
    0.58
     stain
    0.58
     splashing
    0.57
    Activations Density 0.407%

    No Known Activations