© 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. 2-GEMMASCOPE-RES-16K
    11. 12245
    Prev
    Next
    INDEX
    Explanations

    references to the term "San" or "Sanitized."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.63
    SharedDtor
    -0.41
     propOrder
    -0.39
    xtext
    -0.39
    writeField
    -0.39
    分から
    -0.38
    actionMode
    -0.38
     disambiguazione
    -0.37
    ellation
    -0.36
     Beatrix
    -0.36
    POSITIVE LOGITS
     san
    3.17
    san
    3.03
    San
    2.95
     San
    2.83
     SAN
    2.81
    SAN
    2.69
     sanction
    2.30
     Сан
    2.13
     Sanford
    2.03
     sanctions
    2.02
    Activations Density 0.374%

    No Known Activations