© 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. 247
    Prev
    Next
    INDEX
    Explanations

    references to institutions or locations in a formal context, particularly focusing on educational and financial entities

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

    "in," "of," "over," or "across" preceding a location

    np_acts-logits-general · gemini-2.0-flash

    prepositions and geographical entities

    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
    XmlAccessorType
    -0.70
    UnusedPrivate
    -0.70
     ComVisible
    -0.69
     BoxDecoration
    -0.68
    MigrationBuilder
    -0.66
     linkovi
    -0.63
    bootstrapcdn
    -0.62
     iſt
    -0.60
     ſind
    -0.60
    PreferredItem
    -0.59
    POSITIVE LOGITS
     Hong
    0.74
    
    0.72
    afficheront
    0.69
     Manitoba
    0.64
     Texas
    0.64
     Colorado
    0.63
     Singapore
    0.61
     Sri
    0.60
     Saskatchewan
    0.60
     Australian
    0.59
    Activations Density 1.674%

    No Known Activations