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

    Neuronpedia

    APICircuit 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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1902
    Prev
    Next
    INDEX
    Explanations

    references to various types of boats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.84
     متعلقه
    -0.83
    ága
    -0.78
     Lel
    -0.77
     Sparkle
    -0.70
     McNally
    -0.69
    pering
    -0.69
    }}},
    -0.68
     Emery
    -0.68
    Ẽ
    -0.68
    POSITIVE LOGITS
     boats
    1.67
    boat
    1.67
     BOAT
    1.63
     boat
    1.60
    Boat
    1.55
     Boat
    1.54
     Boats
    1.45
    boats
    1.44
    Boats
    1.34
     boating
    1.07
    Activations Density 0.023%

    No Known Activations