© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 951
    Prev
    Next
    INDEX
    Explanations

    aspects related to family properties or residences

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

    describing property or land

    np_acts-logits-general · gemini-2.0-flash

    rural properties and estates

    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
    #+#
    -0.79
    AndEndTag
    -0.73
    bootstrapcdn
    -0.73
    MLLoader
    -0.68
    STREET
    -0.64
    streets
    -0.64
     ProtoMessage
    -0.64
     Chinatown
    -0.63
     Suez
    -0.62
    MigrationBuilder
    -0.62
    POSITIVE LOGITS
     farm
    1.25
     rural
    1.19
     farmhouse
    1.07
     ranch
    1.06
     countryside
    1.05
     rustic
    1.05
     farms
    1.03
    farm
    0.99
    Rural
    0.98
     Farm
    0.98
    Activations Density 0.274%

    No Known Activations