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. 3-GEMMASCOPE-RES-16K
    6. 12550
    Prev
    Next
    INDEX
    Explanations

    references to boats and boating activities

    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
    cetamol
    -0.68
     Titre
    -0.65
    Ẽ
    -0.64
    pering
    -0.64
    یریت
    -0.64
     Lel
    -0.61
    zuli
    -0.61
    داً
    -0.61
     Rand
    -0.59
    ÊNCIAS
    -0.59
    POSITIVE LOGITS
     boat
    3.15
    boat
    3.02
     boats
    2.91
     Boat
    2.88
    Boat
    2.87
     BOAT
    2.79
    boats
    2.63
     Boats
    2.52
    Boats
    2.27
     boating
    1.83
    Activations Density 0.035%

    No Known Activations