Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1553
    Prev
    Next
    INDEX
    Explanations

    terms related to golf carts and their features

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

    Small vehicles or personal transportation

    np_acts-logits-general · gemini-2.0-flash

    wheeled personal transport

    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
     Chwiliwch
    -0.65
    MigrationBuilder
    -0.58
    Билгалдахарш
    -0.58
    nasel
    -0.56
     nahilalakip
    -0.55
    مصادر
    -0.52
     albumin
    -0.51
    ंदीखरीदारी
    -0.50
    AddHtmlAttribute
    -0.50
    windowFixed
    -0.49
    POSITIVE LOGITS
     scooters
    0.82
     scooter
    0.82
     motorized
    0.81
     riding
    0.81
     skateboard
    0.81
     skate
    0.81
    🛴
    0.73
     Skate
    0.73
     ATV
    0.72
     ride
    0.72
    Activations Density 0.139%

    No Known Activations