© 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. 16-GEMMASCOPE-RES-65K
    11. 27747
    Prev
    Next
    INDEX
    Explanations

    key terms related to aviation and airline operations

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

    just the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OMITBAD
    -0.75
     OnInit
    -0.75
     Efq
    -0.74
     autorytatywna
    -0.68
    CloseOperation
    -0.68
    ensores
    -0.67
    MLLoader
    -0.66
    RTEX
    -0.63
    AndEndTag
    -0.63
    didSet
    -0.63
    POSITIVE LOGITS
     passenger
    1.02
     passengers
    1.02
     airline
    0.93
     Passenger
    0.92
    Passenger
    0.90
     Passengers
    0.86
     travel
    0.81
    passenger
    0.80
     Airlines
    0.78
     Travel
    0.77
    Activations Density 0.067%

    No Known Activations