© 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. 13665
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to strong feelings or significant events

    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
     مشين
    -0.82
     CreateTagHelper
    -0.82
    Autoritní
    -0.76
     跳转至
    -0.76
     myſelf
    -0.74
    testens
    -0.74
     Jefus
    -0.73
     Monfieur
    -0.72
    transQ
    -0.71
    endfor
    -0.69
    POSITIVE LOGITS
     it
    0.64
     could
    0.62
     entire
    0.59
     make
    0.56
     even
    0.55
     actually
    0.54
     making
    0.53
     des
    0.53
     actual
    0.52
     cause
    0.50
    Activations Density 0.112%

    No Known Activations