© 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. 20-GEMMASCOPE-RES-16K
    11. 14603
    Prev
    Next
    INDEX
    Explanations

    structural details about buildings

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

    height and buildings

    np_acts-logits-general · gemini-2.0-flash

    twin towers and tall buildings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cottage
    -0.57
     Farmhouse
    -0.52
     cottage
    -0.48
     farmhouse
    -0.47
     rurale
    -0.46
    cottage
    -0.46
    Rüyada
    -0.46
     familiari
    -0.46
     agricoles
    -0.44
     homeschool
    -0.44
    POSITIVE LOGITS
     tallest
    1.35
     tower
    1.32
     towers
    1.26
     skyscraper
    1.25
     Tower
    1.17
     skyscrapers
    1.16
     Towers
    1.11
     elevators
    1.10
     tall
    1.10
    tall
    1.07
    Activations Density 0.139%

    No Known Activations