Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15409
    Prev
    Next
    INDEX
    Explanations

    mentions of ships and maritime-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.77
     unison
    -0.70
     diſt
    -0.68
     Idem
    -0.66
     Lest
    -0.64
    έλ
    -0.63
     zouden
    -0.62
     pleaſure
    -0.62
     parlamentar
    -0.61
     Endlich
    -0.61
    POSITIVE LOGITS
     ship
    1.70
     ships
    1.62
     Ship
    1.57
     SHIP
    1.56
     Ships
    1.56
    Ships
    1.45
    Ship
    1.43
    ship
    1.39
    ships
    1.33
    SHIP
    1.30
    Activations Density 0.050%

    No Known Activations