© 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. 12-GEMMASCOPE-RES-16K
    6. 2539
    Prev
    Next
    INDEX
    Explanations

    terms associated with nitrogen and its role in organic compounds and fertilizers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.80
     venons
    -0.71
     Automat
    -0.70
    uolo
    -0.68
    cmath
    -0.65
     CountDown
    -0.64
    र्शन
    -0.64
     Starlight
    -0.63
    CDCl
    -0.63
    Награды
    -0.62
    POSITIVE LOGITS
     Nitrogen
    1.05
     nitrogen
    1.03
    BeginContext
    0.93
     Lup
    0.92
    Nitrogen
    0.90
    Lup
    0.89
    XtraGrid
    0.87
    nitrogen
    0.83
     Ife
    0.77
     Neph
    0.75
    Activations Density 0.747%

    No Known Activations