© 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. 24-GEMMASCOPE-RES-16K
    11. 2026
    Prev
    Next
    INDEX
    Explanations

    references to specific architectural structures or buildings

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

    Buildings, especially towers and hotels

    np_acts-logits-general · gemini-2.0-flash

    buildings and hotels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.71
    ArgumentParser
    -0.64
     protoimpl
    -0.62
    jsxFileName
    -0.59
    InjectAttribute
    -0.56
    angliski
    -0.55
    expandindo
    -0.55
    enumi
    -0.55
    bindParam
    -0.55
    openSession
    -0.54
    POSITIVE LOGITS
     tower
    1.20
     tallest
    1.13
     towers
    1.09
     Tower
    1.01
     tall
    0.93
     skyscraper
    0.92
    tall
    0.91
    tower
    0.91
     Skys
    0.89
     skyscrapers
    0.88
    Activations Density 0.177%

    No Known Activations