© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 9472
    Prev
    Next
    INDEX
    Explanations

    sections that indicate strong emotional states or sentiments, often represented by underscores or blank spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.89
    Personensuche
    -0.85
    DoubleQuotes
    -0.83
     تضيفلها
    -0.83
    SharedDtor
    -0.82
    RenderAtEndOf
    -0.82
     للمعارف
    -0.81
     تانيه
    -0.80
    出版年
    -0.79
    />";
    -0.78
    POSITIVE LOGITS
    ________________
    1.12
    __
    0.99
    ____
    0.87
    ___
    0.86
    ______
    0.81
    ________
    0.77
    __________
    0.76
    _______
    0.75
    _________
    0.75
    ___________
    0.73
    Activations Density 0.096%

    No Known Activations