© 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. 24-GEMMASCOPE-RES-16K
    11. 2565
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fly" or related forms, indicating references to flight or flying

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

    flying or movement

    np_acts-logits-general · gemini-2.0-flash

    flying saucer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بوابة
    -0.65
    Personensuche
    -0.56
     wireType
    -0.54
    WriteTagHelper
    -0.51
     gemeint
    -0.51
    XmlAccessorType
    -0.50
    НИК
    -0.49
     للاسماء
    -0.49
    قایناقلار
    -0.49
    toks
    -0.48
    POSITIVE LOGITS
     kites
    0.57
    ArrowToggle
    0.56
     समीक्षक
    0.56
     saucer
    0.56
     Nimbus
    0.53
     overhead
    0.52
     above
    0.52
     solo
    0.51
     ointment
    0.51
    تقاوى
    0.51
    Activations Density 0.098%

    No Known Activations