© 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. 30-GEMMASCOPE-RES-16K
    11. 14849
    Prev
    Next
    INDEX
    Explanations

    phrases related to recommendations and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Household or travel items

    np_acts-logits-general · gemini-2.0-flash

    portable supplies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fisuras
    -0.64
     orejas
    -0.61
     bocetos
    -0.57
     näin
    -0.57
     vueltas
    -0.56
     Versorgung
    -0.56
     ganancias
    -0.56
     Gedanke
    -0.56
     niebla
    -0.56
     agujeros
    -0.56
    POSITIVE LOGITS
     refrigerator
    0.99
     refrigerators
    0.96
     laptop
    0.94
     laptops
    0.92
     ovens
    0.92
     binoculars
    0.92
     sunglasses
    0.92
     headphones
    0.92
     fridge
    0.90
     stoves
    0.89
    Activations Density 0.875%

    No Known Activations