© 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. 1-GEMMASCOPE-RES-16K
    6. 14669
    Prev
    Next
    INDEX
    Explanations

    references to "jet" in various contexts, likely focusing on concepts related to jet propulsion or jet engines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jorg
    -0.51
    容易
    -0.50
     Jerry
    -0.48
     straw
    -0.48
     Frans
    -0.48
    UpDown
    -0.47
     propor
    -0.47
    sim
    -0.46
    Frans
    -0.45
    GR
    -0.45
    POSITIVE LOGITS
     jet
    1.22
     Jet
    1.14
    Jet
    1.13
    jet
    1.04
    JET
    0.90
     gynhyrchwyd
    0.87
    ValueStyle
    0.86
     JET
    0.85
     jets
    0.82
    TagMode
    0.81
    Activations Density 0.063%

    No Known Activations