© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 2856
    Prev
    Next
    INDEX
    Explanations

    terms related to aerospace and military exports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 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
    TagMode
    -0.40
    radores
    -0.35
     Ruhe
    -0.34
    posób
    -0.33
    DOCTYPE
    -0.32
    RETT
    -0.32
    pl
    -0.32
     nimi
    -0.31
     ruchu
    -0.31
    plo
    -0.31
    POSITIVE LOGITS
    FormTagHelper
    0.66
    httphttps
    0.62
     незавершена
    0.58
    rawDesc
    0.56
    richTextPanel
    0.54
    BufferException
    0.54
    Diweddarwch
    0.53
     BrowserModule
    0.53
     manufact
    0.52
     StatelessWidget
    0.52
    Activations Density 0.425%

    No Known Activations