© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9319
    Prev
    Next
    INDEX
    Explanations

    references to various forms of the word "sn" or related terms

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

    "SN" or "Sn" followed by a number/other characters

    np_acts-logits-general · gemini-2.0-flash

    sn prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.50
    󠁮
    -0.47
    richTextPanel
    -0.42
    олові
    -0.39
    Παραπομπές
    -0.39
     initComponents
    -0.39
    RTEE
    -0.39
    IntoConstraints
    -0.38
    !("{}",
    -0.38
    jmniej
    -0.38
    POSITIVE LOGITS
     sn
    0.74
     Sna
    0.65
     Sn
    0.63
    sn
    0.62
     SN
    0.61
     snap
    0.58
    Sn
    0.58
     sna
    0.57
     sni
    0.57
    sna
    0.56
    Activations Density 0.243%

    No Known Activations