© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 16219
    Prev
    Next
    INDEX
    Explanations

    references to parking lots and related facilities

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

    "parking" or "parking lot"

    np_acts-logits-general · gemini-2.0-flash

    parking lot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.58
     autorytatywna
    -0.54
    tsch
    -0.48
     cytoplasm
    -0.47
    ussis
    -0.47
    Factories
    -0.46
    stry
    -0.46
     pesta
    -0.46
     Zimmer
    -0.45
    entium
    -0.45
    POSITIVE LOGITS
     parking
    2.13
     Parking
    1.89
    parking
    1.78
    Parking
    1.77
     PARKING
    1.76
     parked
    1.40
     parcheggio
    1.36
     parkir
    1.34
     Parkplatz
    1.27
     estacionamento
    1.21
    Activations Density 0.071%

    No Known Activations