© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 108328
    Prev
    Next
    INDEX
    Explanations

    mentions of hospitals and healthcare facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hospital
    -1.48
     Hospital
    -1.32
     hospitals
    -1.30
    Hospital
    -1.29
     HOSPITAL
    -1.17
    hospital
    -1.16
    Hospitals
    -1.15
     Hospitals
    -1.13
     szpital
    -1.12
     hospitales
    -1.11
    POSITIVE LOGITS
     utafitiHapana
    0.47
    Източници
    0.41
     Meno
    0.39
    Доро
    0.39
    Viited
    0.38
    脚注の使い方
    0.38
     invent
    0.38
     chữ
    0.37
    DllImport
    0.37
    WebMethod
    0.36
    Activations Density 0.007%

    No Known Activations