© 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. 3-GEMMASCOPE-RES-16K
    6. 7110
    Prev
    Next
    INDEX
    Explanations

    references to naval and maritime themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amqp
    -0.50
     grond
    -0.49
     Valley
    -0.47
     snowing
    -0.46
     aspen
    -0.46
    ellido
    -0.44
     SNOW
    -0.43
     FormBuilder
    -0.42
     Malvern
    -0.42
     Midlands
    -0.42
    POSITIVE LOGITS
     marine
    1.39
     seafood
    1.34
     coastal
    1.33
     maritime
    1.32
     seawater
    1.32
     nautical
    1.29
     sailing
    1.28
     naval
    1.27
     sea
    1.27
     sailed
    1.27
    Activations Density 2.242%

    No Known Activations