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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 13457
    Prev
    Next
    INDEX
    Explanations

    references related to boats and vessels

    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
     nodig
    -0.65
    cetamol
    -0.58
    dics
    -0.55
     Cullen
    -0.54
    baran
    -0.52
    hige
    -0.50
     Jacobs
    -0.48
    粹
    -0.48
    jLabel
    -0.47
    داً
    -0.46
    POSITIVE LOGITS
     boat
    4.39
    boat
    4.14
     Boat
    3.98
    Boat
    3.92
     boats
    3.73
     BOAT
    3.71
    boats
    3.51
     Boats
    3.35
    Boats
    2.88
     boating
    2.51
    Activations Density 0.053%

    No Known Activations