© 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. 20-GEMMASCOPE-RES-16K
    6. 11702
    Prev
    Next
    INDEX
    Explanations

    terms related to changes and phenomena in agricultural practices or industries

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

    associated with vanishing or becoming obsolete

    np_acts-logits-general · gemini-2.0-flash

    became extinct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ViewImports
    -0.67
    Personendaten
    -0.60
    はじめに
    -0.60
    قایناق‌لار
    -0.59
    Rujuakan
    -0.58
    SourceChecksum
    -0.56
     desblo
    -0.55
     بيها
    -0.54
    ://$
    -0.53
     Вікі
    -0.52
    POSITIVE LOGITS
     disappeared
    2.06
     vanished
    1.89
     disappear
    1.77
     disappears
    1.77
     disappearing
    1.74
     desapare
    1.58
     disappearance
    1.55
     vanish
    1.52
     extinct
    1.49
     vanishes
    1.45
    Activations Density 0.792%

    No Known Activations