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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 11779
    Prev
    Next
    INDEX
    Explanations

    references to public transit and transportation networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.70
     CURIAM
    -0.69
     doGet
    -0.57
    ANTLR
    -0.56
    KeySpec
    -0.56
    ųjų
    -0.53
    EndContext
    -0.51
     SqlCommand
    -0.50
    MLLoader
    -0.50
    ImageIO
    -0.50
    POSITIVE LOGITS
     buses
    0.72
     bus
    0.68
     Buses
    0.65
     fleet
    0.65
     fleets
    0.61
    Buses
    0.59
    RegistryLite
    0.57
     autobuses
    0.55
    buses
    0.55
    🚍
    0.55
    Activations Density 0.199%

    No Known Activations