© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 790
    Prev
    Next
    INDEX
    Explanations

    the salutation "dear" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    mtd
    -0.92
    ResponseWriter
    -0.85
    HasBeenSet
    -0.85
    ViewFeatures
    -0.83
    Witt
    -0.78
    AppMethodBeat
    -0.73
    ChangeEvent
    -0.72
     Penrose
    -0.71
     OCS
    -0.70
    pout
    -0.69
    POSITIVE LOGITS
     DEAR
    0.97
     cherished
    0.91
     Dear
    0.88
     dear
    0.87
    DEAR
    0.87
     treasured
    0.84
     precious
    0.82
     beloved
    0.80
     chers
    0.78
    Beloved
    0.76
    Activations Density 0.109%

    No Known Activations