© 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. 857
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "Tro" in various forms, likely related to medical or scientific nomenclature

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

    Texts containing "Trofile" or "Tro" followed by lowercase letters

    np_acts-logits-general · gemini-2.0-flash

    words starting with Tro

    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
    matics
    -0.66
    ?>"
    -0.61
    }');
    -0.57
    ClientSize
    -0.56
    ollectionView
    -0.56
    }';
    -0.56
     formality
    -0.54
    XmlRootElement
    -0.54
    )";
    -0.53
    ##
    -0.53
    POSITIVE LOGITS
     autorytatywna
    0.81
     Tro
    0.79
    Tro
    0.68
     TRO
    0.67
     tro
    0.59
    tro
    0.57
     cherchés
    0.57
    writeFieldEnd
    0.54
     Trot
    0.54
     oslo
    0.54
    Activations Density 0.118%

    No Known Activations