© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 33-GEMMASCOPE-RES-16K
    11. 9145
    Prev
    Next
    INDEX
    Explanations

    elements of JSON-like structures or data serialization methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.71
     surla
    -0.66
     оригіналу
    -0.66
    bootstrapcdn
    -0.63
    ViewImports
    -0.60
    BufferException
    -0.60
    CloseOperation
    -0.59
     мәкал
    -0.57
     
    -0.57
    QMetaType
    -0.57
    POSITIVE LOGITS
            
    0.68
             
    0.41
    awtextra
    0.40
           
    0.40
    skine
    0.37
    Новости
    0.37
    　　　
    0.34
    bibfield
    0.33
          
    0.33
    chieht
    0.30
    Activations Density 0.307%

    No Known Activations