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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 7251
    Prev
    Next
    INDEX
    Explanations

    mentions of auctions and the "Star Wars" franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CPtr
    -0.76
    RenderAtEndOf
    -0.73
    sizeCache
    -0.71
     архивлан
    -0.71
    rature
    -0.70
    MessageOf
    -0.70
    esgue
    -0.70
    OGND
    -0.69
     Exacts
    -0.69
     ***!
    -0.69
    POSITIVE LOGITS
     collision
    0.95
     Tick
    0.93
    Tick
    0.90
     tick
    0.81
    ling
    0.81
    collision
    0.80
     auction
    0.79
    tick
    0.79
    ales
    0.77
     Collision
    0.77
    Activations Density 0.047%

    No Known Activations