© 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. 1-GEMMASCOPE-RES-16K
    11. 9418
    Prev
    Next
    INDEX
    Explanations

    instances of the word "port."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.60
     simpat
    -0.41
     Baby
    -0.38
    MainActivity
    -0.38
    primaryStage
    -0.34
    thread
    -0.34
     QUI
    -0.33
    por
    -0.33
    כא
    -0.33
     Wass
    -0.32
    POSITIVE LOGITS
     palm
    0.83
    Palm
    0.78
     Palm
    0.76
    Hentet
    0.72
     Port
    0.70
    palm
    0.70
    ConstraintMaker
    0.68
     port
    0.68
    Port
    0.67
     estekak
    0.65
    Activations Density 0.203%

    No Known Activations