© 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. 33-GEMMASCOPE-RES-16K
    11. 11225
    Prev
    Next
    INDEX
    Explanations

    JavaScript functions and method calls related to AJAX requests

    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
    ymce
    -0.44
    Obrázky
    -0.42
     Meksiko
    -0.41
     "..\..\
    -0.38
    ранда
    -0.37
    oneofs
    -0.36
    silience
    -0.36
    libatkan
    -0.36
    aux
    -0.36
     oatmeal
    -0.35
    POSITIVE LOGITS
     Propel
    0.53
     sf
    0.52
    
    0.48
    帖最后由
    0.46
     विश्वसनीयता
    0.46
    Propel
    0.44
    liferay
    0.42
    balleur
    0.41
    sf
    0.41
     Peer
    0.41
    Activations Density 0.145%

    No Known Activations