© 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. 27-GEMMASCOPE-RES-16K
    11. 11569
    Prev
    Next
    INDEX
    Explanations

    instances of racial interactions and perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TargetException
    -0.48
     tijden
    -0.43
     functie
    -0.38
    rrggbb
    -0.36
     طی
    -0.35
     dezvol
    -0.34
     ontwikkel
    -0.34
     InputDecoration
    -0.33
     HttpNotFound
    -0.33
    higer
    -0.32
    POSITIVE LOGITS
     passers
    0.87
     tourists
    0.77
     strangers
    0.75
     patrons
    0.72
     shoppers
    0.70
     overheard
    0.66
    tourist
    0.65
     politely
    0.64
    standers
    0.64
     pedestrians
    0.64
    Activations Density 0.302%

    No Known Activations