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. 2-GEMMASCOPE-RES-16K
    6. 6167
    Prev
    Next
    INDEX
    Explanations

    terms related to traffic conditions and incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.80
     initComponents
    -0.77
     resourceCulture
    -0.71
     avenger
    -0.71
    evos
    -0.70
    ///</
    -0.69
    Datuak
    -0.68
     yyl
    -0.68
    RegressionTest
    -0.67
    Organisateur
    -0.66
    POSITIVE LOGITS
     traffic
    1.57
    traffic
    1.44
     Traffic
    1.40
    Traffic
    1.37
     TRAFFIC
    1.30
     trafic
    1.04
     tráfico
    1.01
     highways
    0.94
     Highway
    0.87
     highway
    0.86
    Activations Density 0.061%

    No Known Activations