© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1287
    Prev
    Next
    INDEX
    Explanations

    terms related to lipids and their biochemical properties

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

    phosphatidyl-containing lipid molecules and their chemical components.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.68
     otomatig
    -0.65
    IndentedString
    -0.58
     ویکی‌پدی
    -0.57
     censiti
    -0.56
     propOrder
    -0.52
    resizingMask
    -0.52
     محفوظة
    -0.52
    NameInMap
    -0.52
     Infór
    -0.49
    POSITIVE LOGITS
    ا
    0.55
     Boas
    0.50
    acat
    0.48
    az
    0.47
    ac
    0.47
    ap
    0.47
    ad
    0.47
    ak
    0.46
    ab
    0.45
    ag
    0.45
    Activations Density 0.993%

    No Known Activations