© 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. 36-GEMMASCOPE-RES-16K
    11. 5274
    Prev
    Next
    INDEX
    Explanations

    references to positive social interactions and feelings

    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
    RegressionTest
    -0.44
     &___
    -0.35
    انجليز
    -0.33
     odst
    -0.33
     Paglinawan
    -0.32
     yyr
    -0.32
    uParam
    -0.32
     Picchu
    -0.31
    どうしても
    -0.31
     attribu
    -0.31
    POSITIVE LOGITS
     welcome
    3.72
     Welcome
    3.25
     welcomed
    3.16
    welcome
    3.09
     welcomes
    3.05
     welcoming
    3.03
     WELCOME
    3.03
    Welcome
    3.03
    WELCOME
    2.70
     bienvenida
    2.47
    Activations Density 0.317%

    No Known Activations