© 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. 15-GEMMASCOPE-RES-16K
    6. 11926
    Prev
    Next
    INDEX
    Explanations

    references to data and its management in document formatting or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Superhosts
    -0.70
     rosse
    -0.67
     tribune
    -0.66
    ExtendWith
    -0.66
     Resolver
    -0.65
    RTLE
    -0.65
     Convertible
    -0.64
    Arn
    -0.64
     Tortoise
    -0.64
     Obispo
    -0.64
    POSITIVE LOGITS
     data
    1.52
     DATA
    1.48
     Data
    1.47
    DATA
    1.44
    data
    1.29
    Data
    1.24
     Daten
    1.20
     GetData
    1.20
     datas
    1.20
     setData
    1.19
    Activations Density 0.117%

    No Known Activations