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

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 10246
    Prev
    Next
    INDEX
    Explanations

    repeated use of the word "they" in various grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.66
     itself
    -0.60
    itself
    -0.58
     EconPapers
    -0.54
    its
    -0.54
     its
    -0.53
    ArrowToggle
    -0.50
     itſelf
    -0.47
    Slf
    -0.44
    IsContent
    -0.44
    POSITIVE LOGITS
     themselves
    1.13
    themselves
    0.98
    Their
    0.98
     Their
    0.92
     berdua
    0.87
    their
    0.81
     fleste
    0.79
     their
    0.76
     Lordships
    0.74
     Их
    0.71
    Activations Density 0.258%

    No Known Activations