© 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. 648
    Prev
    Next
    INDEX
    Explanations

    references to historical events related to World War I

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

    historical and biographical information, particularly related to military service

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

    World War I

    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
    ThroughAttribute
    -0.90
     متعلقه
    -0.85
    webElementXpaths
    -0.81
     ब्रेकडाउन
    -0.79
    afficheront
    -0.74
    ⓧ
    -0.74
    TagHelper
    -0.74
    Portale
    -0.73
    InputBorder
    -0.73
     Numerade
    -0.72
    POSITIVE LOGITS
     Somme
    0.61
     trench
    0.57
     Galli
    0.50
     trenches
    0.50
    chées
    0.48
     Flanders
    0.46
    endphp
    0.45
     dead
    0.44
     Argonne
    0.42
     Dead
    0.42
    Activations Density 0.066%

    No Known Activations