© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12483
    Prev
    Next
    INDEX
    Explanations

    instances of quotation marks or apostrophes, particularly in the context of dialogue or citations

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

    ending with "'s" or "’s"

    np_acts-logits-general · gemini-2.0-flash

    possessives, contractions, and common figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mr
    -0.58
    ￡
    -0.55
    Mr
    -0.50
    ParallelGroup
    -0.50
     th
    -0.48
     G
    -0.46
     Heil
    -0.45
     AP
    -0.45
     MR
    -0.44
    Heil
    -0.44
    POSITIVE LOGITS
     themſelves
    0.94
     himſelf
    0.94
     itſelf
    0.90
     myſelf
    0.89
     Jefus
    0.88
     leaſt
    0.86
     Houſe
    0.86
     purpoſe
    0.85
     uſe
    0.84
     becauſe
    0.83
    Activations Density 0.097%

    No Known Activations