© 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. 16-GEMMASCOPE-RES-16K
    11. 13357
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their related terminology

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

    Starts with "ath," "eth," "uth," or "th"

    np_acts-logits-general · gemini-2.0-flash

    Ath-/Arth-/Eth- prefixes for medical/athletic terms

    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
    er
    -0.91
    ChildScrollView
    -0.89
     وتسجيلات
    -0.89
    )|^{
    -0.79
    ExecuteReader
    -0.79
     Wilber
    -0.76
     Serr
    -0.74
     verily
    -0.74
    #
    -0.73
    quiao
    -0.73
    POSITIVE LOGITS
    ATH
    1.08
    TH
    0.98
    ath
    0.98
     Nath
    0.94
     Lath
    0.94
     TH
    0.92
    uth
    0.91
    lith
    0.91
     ATH
    0.91
    alth
    0.88
    Activations Density 0.340%

    No Known Activations