© 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. 1493
    Prev
    Next
    INDEX
    Explanations

    keywords and terms related to performance analytics and operational efficiency

    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
     Hay
    -0.38
    ded
    -0.38
    Localisation
    -0.38
    /
    -0.37
    etted
    -0.36
    ρή
    -0.36
    ssa
    -0.35
     pits
    -0.35
    ISupport
    -0.35
    ρω
    -0.35
    POSITIVE LOGITS
    +#+#
    0.91
    extAlignment
    0.79
    ConstraintMaker
    0.68
    rawDesc
    0.68
    Personendaten
    0.68
    setViewportView
    0.67
     مشين
    0.66
    IntoConstraints
    0.65
     ويكيميديا
    0.64
    InputBorder
    0.64
    Activations Density 2.037%

    No Known Activations