© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10788
    Prev
    Next
    INDEX
    Explanations

    references to springs and rings

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

    The neuron identifies the word "spring" in various contexts, including as a mechanical device, a season, or part of compound terms like "spring-mounted".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )])
    -0.57
    ).)
    -0.54
    ')))
    -0.54
    )•
    -0.53
     })
    
    -0.51
    })}\
    -0.51
     dataTable
    -0.51
     })}
    -0.51
     NavController
    -0.50
     ostavi
    -0.49
    POSITIVE LOGITS
     Wing
    0.77
     RING
    0.76
    ring
    0.75
    RING
    0.75
     Pring
    0.75
     Ring
    0.74
    Wing
    0.74
    Ring
    0.71
     WING
    0.69
    wing
    0.68
    Activations Density 0.112%

    No Known Activations