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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 3244
    Prev
    Next
    INDEX
    Explanations

    terms related to traffic regulations and signs

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

    traffic signals/intersections

    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 @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
     Normdatei
    -0.72
    ]")]
    -0.68
     transfieras
    -0.65
     الاطلاع
    -0.63
     Offisielt
    -0.63
    Билгалдахарш
    -0.60
    ValueGeneration
    -0.59
    evos
    -0.59
    ledad
    -0.57
    POSITIVE LOGITS
     intersection
    1.25
     intersections
    1.12
     traffic
    1.09
     crossing
    1.06
     cross
    0.92
     stop
    0.92
     crossings
    0.92
     signal
    0.90
    intersection
    0.89
     Intersection
    0.89
    Activations Density 0.113%

    No Known Activations