© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1291
    Prev
    Next
    INDEX
    Explanations

    references to the name "Lea" or variations of it

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

    mentions of the name "Leahy."

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

    Lea and Lévy phrases

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Hermans
    -0.59
    endt
    -0.56
    errHandler
    -0.55
    起
    -0.54
    TAINMENT
    -0.53
     namanya
    -0.52
    lio
    -0.52
     confé
    -0.51
     Bebe
    -0.49
     Schwert
    -0.49
    POSITIVE LOGITS
    Lea
    1.22
     Lea
    1.21
     lea
    0.84
     Roskov
    0.83
     Autorizaciones
    0.66
     @"/
    0.66
    ]=>
    0.65
    CppMethod
    0.64
    __":
    0.64
    Leaky
    0.63
    Activations Density 0.023%

    No Known Activations