© 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. 0-GEMMASCOPE-RES-16K
    11. 8191
    Prev
    Next
    INDEX
    Explanations

    occurrences of "DO" in different contexts, particularly in programming or coding-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.94
    Personendaten
    -0.88
     transfieras
    -0.87
    ########.
    -0.79
     disambiguazione
    -0.79
     محفوظة
    -0.78
    ChildScrollView
    -0.76
    хьтан
    -0.75
    帖最后由
    -0.75
     abstrait
    -0.75
    POSITIVE LOGITS
     đ
    0.48
    <eos>
    0.40
    ,
    0.38
     воз
    0.37
      
    0.37
     
    0.35
     Sea
    0.35
    ผ
    0.34
     Esc
    0.34
    lifer
    0.34
    Activations Density 0.234%

    No Known Activations