© 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. 12-GEMMASCOPE-RES-16K
    6. 7095
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to technical topics and detailed descriptions in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    дель
    -0.65
     wide
    -0.65
     Gers
    -0.63
    !
    -0.61
    ш
    -0.60
    grpc
    -0.59
     Tsche
    -0.58
    bs
    -0.57
     Zustimmung
    -0.57
    rag
    -0.56
    POSITIVE LOGITS
    تقاوى
    0.97
     deepened
    0.92
     Simplify
    0.92
    tened
    0.91
    tening
    0.91
     softens
    0.90
     gild
    0.89
    ValueStyle
    0.89
    /*---
    0.88
    ENED
    0.87
    Activations Density 0.325%

    No Known Activations