© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10156
    Prev
    Next
    INDEX
    Explanations

    references to a specific group of individuals involved in a study or research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     juſ
    -0.82
    :✨
    -0.82
    berdayakan
    -0.76
    PerformLayout
    -0.76
    Personendaten
    -0.76
    DeleteBehavior
    -0.75
     purpoſe
    -0.74
    migrationBuilder
    -0.74
    Демографія
    -0.73
     dreamstime
    -0.73
    POSITIVE LOGITS
     विश्वसनीयता
    0.68
    fortawesome
    0.64
     aid
    0.61
     pak
    0.60
    mente
    0.58
     Aid
    0.57
     aids
    0.57
    nter
    0.56
    aid
    0.55
     aide
    0.55
    Activations Density 0.058%

    No Known Activations