© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15528
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to "sn" in various contexts, including different spellings and combinations

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

    Tokens starting with "Sn" or "sn"

    np_acts-logits-general · gemini-2.0-flash

    words starting with sn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    partement
    -0.56
    Currencies
    -0.54
    suya
    -0.52
     Basu
    -0.52
     Part
    -0.51
    JULY
    -0.51
     Millar
    -0.51
     Aria
    -0.51
    GeneratedValue
    -0.51
     Zak
    -0.51
    POSITIVE LOGITS
     sn
    1.01
     Sn
    1.01
    Sn
    0.94
    Snoo
    0.93
     Sna
    0.87
     SN
    0.87
    sn
    0.86
     Monfieur
    0.85
     مرئيه
    0.79
     sni
    0.79
    Activations Density 0.150%

    No Known Activations