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. 4620
    Prev
    Next
    INDEX
    Explanations

    terms related to traffic signals and their regulations

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

    Road intersections and traffic signals

    np_acts-logits-general · gemini-2.0-flash

    traffic signals and intersections

    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
    Chham
    -0.81
     transfieras
    -0.65
    Välislingid
    -0.63
    ekt
    -0.62
    ✭
    -0.62
     الاطلاع
    -0.60
    Datuak
    -0.58
     allAfrica
    -0.57
    ilerini
    -0.57
     unknownFields
    -0.56
    POSITIVE LOGITS
     crossing
    1.42
     crossings
    1.28
     intersection
    1.19
    crossing
    1.19
     cross
    1.18
     traffic
    1.10
     Crossing
    1.09
    cross
    1.05
    Crossing
    1.05
     intersections
    1.05
    Activations Density 0.126%

    No Known Activations