© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3931
    Prev
    Next
    INDEX
    Explanations

    phrases related to loss or losing something

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

    "lost" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    lost or losing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fieldNum
    -0.50
    tagHelper
    -0.50
     AssemblyTitle
    -0.48
     Greet
    -0.48
     ActionListener
    -0.48
    ────────
    -0.47
    DateTimeFormat
    -0.47
    RectangleBorder
    -0.46
     RTE
    -0.46
     CPM
    -0.45
    POSITIVE LOGITS
     loss
    1.27
    Lost
    1.24
    Loss
    1.22
     Loss
    1.18
    lost
    1.16
     Lost
    1.16
     lost
    1.16
     LOSS
    1.14
    loss
    1.12
    Lose
    1.11
    Activations Density 0.090%

    No Known Activations