© 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. 3-GEMMASCOPE-RES-16K
    11. 7809
    Prev
    Next
    INDEX
    Explanations

    terminology related to infrastructure and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ©️
    -0.56
    ="'.$
    -0.54
    ISupport
    -0.53
    ())));
    -0.50
    )?;
    -0.50
     NSMutable
    -0.49
    賀
    -0.48
     חיצוניים
    -0.48
    ')).
    -0.48
     gången
    -0.47
    POSITIVE LOGITS
     propOrder
    0.74
    +#+
    0.71
    wieś
    0.69
    出版年
    0.67
    település
    0.65
    verwijspagina
    0.63
    WireFormatLite
    0.62
    UniformLocation
    0.61
     NgModule
    0.60
     monasteries
    0.60
    Activations Density 1.373%

    No Known Activations