© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7861
    Prev
    Next
    INDEX
    Explanations

    the definite article "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.77
    featureID
    -0.75
    parsedMessage
    -0.73
     JpaRepository
    -0.72
    IUrlHelper
    -0.70
    RefNanny
    -0.68
    oredCriteria
    -0.66
    GenerationType
    -0.65
     wireType
    -0.65
    存于互联网档案馆
    -0.65
    POSITIVE LOGITS
    The
    1.15
     The
    1.05
     the
    0.88
     THE
    0.71
    the
    0.70
    THE
    0.56
    Their
    0.51
    OnThe
    0.48
    InThe
    0.48
    ethe
    0.48
    Activations Density 0.984%

    No Known Activations