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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9379
    Prev
    Next
    INDEX
    Explanations

    references to corresponding data or entities within a scientific or mathematical context

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

    The neuron detects the phrase "the corresponding" when it's used to connect a concept to a related element.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    IVEREF
    -0.61
     propOrder
    -0.54
    IsContent
    -0.54
    awtextra
    -0.48
     AssemblyVersion
    -0.47
    setVerticalGroup
    -0.46
    enderror
    -0.45
    slidesToShow
    -0.44
     Italijani
    -0.44
     يتيمه
    -0.43
    POSITIVE LOGITS
     corresponding
    1.12
     Corresponding
    1.02
    corresponding
    0.96
     correspondiente
    0.85
     accompanying
    0.85
    Corresponding
    0.85
     related
    0.84
     соответству
    0.82
     associated
    0.81
    相应
    0.81
    Activations Density 0.637%

    No Known Activations