© 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. 36-GEMMASCOPE-RES-16K
    11. 13615
    Prev
    Next
    INDEX
    Explanations

    references to compensation and labor practices associated with economic systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.78
     CreateTagHelper
    -0.74
    fromnode
    -0.64
    transQ
    -0.64
     betweenstory
    -0.63
     ProtoMessage
    -0.63
     yyhl
    -0.60
    SourceChecksum
    -0.60
    adaptiveStyles
    -0.60
    tagHelperRunner
    -0.58
    POSITIVE LOGITS
     much
    2.33
    Much
    2.06
    much
    2.06
     Much
    1.95
     MUCH
    1.91
     mucho
    1.66
     far
    1.63
     намного
    1.55
     jauh
    1.54
     гораздо
    1.50
    Activations Density 0.685%

    No Known Activations