© 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. 22-GEMMASCOPE-RES-16K
    11. 10559
    Prev
    Next
    INDEX
    Explanations

    mechanical terms related to aircraft structure and physics

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

    Aircraft wing and airfoil characteristics

    np_acts-logits-general · gemini-2.0-flash

    wing airfoil aerodynamics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.75
    AndEndTag
    -0.75
    HtmlAttribute
    -0.73
     pleaſure
    -0.72
     estimés
    -0.70
    MLLoader
    -0.68
    RegistryLite
    -0.67
    __(/*!
    -0.67
    DispatchToProps
    -0.66
     Etrus
    -0.66
    POSITIVE LOGITS
     leading
    0.62
    Leading
    0.57
     trailing
    0.57
     Leading
    0.57
    leading
    0.56
     wing
    0.54
     chord
    0.53
    Chord
    0.53
    root
    0.50
     stall
    0.50
    Activations Density 0.194%

    No Known Activations