© 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. 7-GEMMASCOPE-RES-16K
    11. 13202
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to transportation methods and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.52
     NUKAT
    -0.43
    nivå
    -0.42
     Democrá
    -0.40
     réfé
    -0.40
     casó
    -0.40
     nivå
    -0.39
    mäß
    -0.39
     wiecz
    -0.38
    avond
    -0.37
    POSITIVE LOGITS
     transport
    2.94
     Transport
    2.64
    transport
    2.61
    Transport
    2.59
     TRANSPORT
    2.48
     transportation
    2.41
     transports
    2.38
     transporte
    2.27
    TRANSPORT
    2.23
     Transportation
    2.19
    Activations Density 0.087%

    No Known Activations