© 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. 17-GEMMASCOPE-RES-16K
    11. 676
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "middle" in various contexts, including social class, demographics, and geographical regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poussière
    -0.68
     magnétique
    -0.62
     devriez
    -0.60
     poudre
    -0.60
     ComVisible
    -0.59
     pitié
    -0.59
     polvere
    -0.58
     Cults
    -0.58
     déchets
    -0.58
     Nato
    -0.57
    POSITIVE LOGITS
     MIDDLE
    1.01
    MIDDLE
    0.92
     Middle
    0.89
    middle
    0.89
     middle
    0.87
    Middle
    0.87
     Middles
    0.83
    middlewares
    0.74
    addGap
    0.74
     Middel
    0.72
    Activations Density 0.086%

    No Known Activations