© 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. 19-GEMMASCOPE-RES-16K
    11. 15141
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to physical or engineering concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonode
    -0.69
     ';
    -0.64
    czaj
    -0.61
    [])
    -0.60
    []
    -0.59
    eseorang
    -0.58
    ":
    -0.58
    dyž
    -0.58
    ']
    -0.57
    spender
    -0.56
    POSITIVE LOGITS
     nahilalakip
    0.94
    WebElementEntity
    0.82
    PRWEB
    0.68
    <eos>
    0.68
    Tembelea
    0.63
    displaystyle
    0.62
    Hauptartikel
    0.61
    lya
    0.59
     ##
    0.59
    teis
    0.56
    Activations Density 2.123%

    No Known Activations