© 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. 35-GEMMASCOPE-RES-16K
    11. 9416
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to the quality and ambiance of places, specifically restaurants and cafes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.63
     EconPapers
    -0.56
    istible
    -0.42
    AndEndTag
    -0.42
     getPage
    -0.42
    rouvez
    -0.41
    Tē
    -0.41
     insoluble
    -0.41
    getDoctrine
    -0.39
    niająca
    -0.39
    POSITIVE LOGITS
     clean
    1.02
     spacious
    1.00
     cozy
    0.99
     cosy
    0.93
     comfortable
    0.92
     tidy
    0.89
     quiet
    0.89
     roomy
    0.84
     quaint
    0.84
     neat
    0.82
    Activations Density 0.159%

    No Known Activations