© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3476
    Prev
    Next
    INDEX
    Explanations

    terms related to aviation and pilot regulations

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

    Aviation, flying, aircraft, and pilots

    np_acts-logits-general · gemini-2.0-flash

    flight instructor

    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
     resourceCulture
    -0.66
     culturelles
    -0.59
     JpaRepository
    -0.50
    Formatting
    -0.50
    uchtigkeit
    -0.50
     RequestMethod
    -0.50
    ữa
    -0.50
    +#+#
    -0.49
    lottesville
    -0.49
    toHave
    -0.48
    POSITIVE LOGITS
     aviation
    1.28
     flight
    1.26
     aircraft
    1.24
     Flight
    1.22
     pilots
    1.19
     flying
    1.14
     Aviation
    1.14
     Aircraft
    1.13
     Pilots
    1.12
    Flight
    1.08
    Activations Density 0.289%

    No Known Activations