© 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. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 7742
    Prev
    Next
    INDEX
    Explanations

    terms related to diseases and their impacts, particularly in the context of livestock and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.59
     EconPapers
    -0.50
    Personendaten
    -0.50
     malades
    -0.49
     thiệu
    -0.49
     enfermo
    -0.46
     kereszt
    -0.46
     malade
    -0.46
     autorytatywna
    -0.45
     Affected
    -0.44
    POSITIVE LOGITS
     fatal
    0.81
     serious
    0.73
     preventable
    0.70
     deadly
    0.69
     devastating
    0.68
     caused
    0.63
     incurable
    0.62
    serious
    0.61
     lethal
    0.59
     severe
    0.59
    Activations Density 0.860%

    No Known Activations