© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8218
    Prev
    Next
    INDEX
    Explanations

    references to airlines and their operations

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

    Arrival, visiting, or movement

    np_acts-logits-general · gemini-2.0-flash

    arrival and presence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.69
    kheim
    -0.64
    ))^
    -0.55
     NSCoder
    -0.55
     overboard
    -0.55
     MotionEvent
    -0.54
     Selamat
    -0.53
    étaire
    -0.53
     Griswold
    -0.52
    scriptId
    -0.52
    POSITIVE LOGITS
     visiting
    0.97
     arriving
    0.93
     visit
    0.89
     visited
    0.87
     visitó
    0.85
     arrived
    0.85
     arrive
    0.84
     arrives
    0.83
     arrival
    0.80
     visits
    0.80
    Activations Density 0.254%

    No Known Activations