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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 74682
    Prev
    Next
    INDEX
    Explanations

    mentions of specific ships and maritime terminology

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

    ships and vessels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    consulté
    -0.47
     Privacidade
    -0.43
     reformas
    -0.42
    CppMethod
    -0.41
     rebaj
    -0.40
     nadar
    -0.39
     trám
    -0.39
     infancia
    -0.38
     Wiltshire
    -0.38
    magini
    -0.38
    POSITIVE LOGITS
     ship
    0.88
     ships
    0.73
     boat
    0.70
    ship
    0.69
     Ship
    0.67
     navire
    0.65
    Ship
    0.64
     schooner
    0.64
    DockStyle
    0.64
     vessel
    0.63
    Activations Density 0.037%

    No Known Activations