© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7461
    Prev
    Next
    INDEX
    Explanations

    terms related to traffic conditions and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dép
    -0.36
     faſt
    -0.35
    SEED
    -0.33
     SEED
    -0.32
     ſhe
    -0.31
    蹶
    -0.30
    aarrggbb
    -0.29
     ſch
    -0.29
    Throwaway
    -0.29
    seed
    -0.29
    POSITIVE LOGITS
     traffic
    2.19
    traffic
    1.91
     Traffic
    1.82
    Traffic
    1.81
     TRAFFIC
    1.65
     congestion
    1.61
     traffico
    1.48
     trafic
    1.44
     trafik
    1.41
     tráfico
    1.38
    Activations Density 0.333%

    No Known Activations