© 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 - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6233
    Prev
    Next
    INDEX
    Explanations

    references to the concept of normality or standard benchmarks in various contexts

    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
     Dreyfus
    -0.72
    Dund
    -0.71
    ktı
    -0.68
     Rides
    -0.65
    💲
    -0.64
     Kishi
    -0.64
    anek
    -0.63
     sphinct
    -0.63
     MongoClient
    -0.62
     Riviera
    -0.62
    POSITIVE LOGITS
     NORMAL
    1.56
     normals
    1.50
     Normal
    1.50
     normal
    1.46
    normal
    1.46
    NORMAL
    1.44
    Normal
    1.43
    ORMAL
    1.34
    normals
    1.27
     Norma
    1.25
    Activations Density 0.094%

    No Known Activations