© 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. 7160
    Prev
    Next
    INDEX
    Explanations

    references to system commands and documentation

    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
    存于互联网档案馆
    -0.86
     CVC
    -0.84
    Mell
    -0.84
    Parcelize
    -0.83
    Nucle
    -0.78
     sement
    -0.77
     Candel
    -0.76
    Castell
    -0.76
    nestjs
    -0.76
     Castell
    -0.75
    POSITIVE LOGITS
     sys
    0.89
    sys
    0.80
     Doc
    0.76
     isAdmin
    0.74
     BEER
    0.73
     Sys
    0.71
    doc
    0.71
     doc
    0.70
    Sys
    0.69
    sue
    0.69
    Activations Density 0.046%

    No Known Activations