© 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. 10-GEMMASCOPE-RES-16K
    11. 13815
    Prev
    Next
    INDEX
    Explanations

    copyright symbols and various related legal or formal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.13
    :✨
    -0.96
    GEBURTSDATUM
    -0.94
     nahilalakip
    -0.93
    VIAF
    -0.91
     CreateTagHelper
    -0.91
    IntoConstraints
    -0.84
    مراجع
    -0.83
     незавершена
    -0.82
    Autoritní
    -0.77
    POSITIVE LOGITS
    FormTagHelper
    0.92
    LayoutStyle
    0.92
    DotNetBar
    0.84
    BagConstraints
    0.83
    addPreferredGap
    0.82
    openqa
    0.82
     defaultstate
    0.79
    AnchorTagHelper
    0.74
    setVerticalGroup
    0.63
    gridx
    0.60
    Activations Density 0.011%

    No Known Activations