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

    Neuronpedia

    Jacobian LensNEW
    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. 14729
    Prev
    Next
    INDEX
    Explanations

    phrasal connections between tolerance, adaptation, and resistance in response to environmental changes

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

    Becoming accustomed to

    np_acts-logits-general · gemini-2.0-flash

    getting used to things

    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
     educativas
    -0.51
     sexes
    -0.51
    蜒
    -0.49
     confé
    -0.47
     medel
    -0.47
    ComponentModel
    -0.47
     auffi
    -0.45
     néz
    -0.45
     Beiträge
    -0.45
     Chriftian
    -0.45
    POSITIVE LOGITS
     accustomed
    1.95
     habitu
    1.70
     acost
    1.67
     привы
    1.66
     acostumb
    1.64
     familiar
    1.60
     habit
    1.56
     familiarity
    1.52
    慣
    1.42
    familiar
    1.40
    Activations Density 0.360%

    No Known Activations