© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5682
    Prev
    Next
    INDEX
    Explanations

    names of teams and players in sports contexts

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

    "Indiana" or "Indianapolis"

    np_acts-logits-general · gemini-2.0-flash

    Indianapolis and Indiana

    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
     matang
    -0.51
    guh
    -0.51
     catalán
    -0.49
     skri
    -0.46
     кӀ
    -0.45
     FLEX
    -0.45
    guero
    -0.44
    ful
    -0.44
    gulp
    -0.44
    endsection
    -0.43
    POSITIVE LOGITS
     Indianapolis
    1.39
     Indiana
    1.38
    Indianapolis
    1.26
    Indiana
    1.24
     Indy
    1.18
     INDIANA
    1.11
    Indy
    1.06
     indiana
    1.00
     Purdue
    0.96
     Hoo
    0.93
    Activations Density 0.106%

    No Known Activations