© 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. 8796
    Prev
    Next
    INDEX
    Explanations

    code-related terms that indicate conditional evaluation or validity

    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
     Wiktionnaire
    -0.46
     intptr
    -0.45
    ंदीखरीदारी
    -0.39
    ècie
    -0.37
     kaarangay
    -0.37
    )$/,
    -0.36
    новништво
    -0.36
    itschrift
    -0.36
    hoga
    -0.35
    bė
    -0.34
    POSITIVE LOGITS
     otherwise
    4.47
     Otherwise
    4.00
    otherwise
    3.92
    Otherwise
    3.91
     OTHERWISE
    3.25
     altrimenti
    3.08
     sonst
    2.86
    否则
    2.78
     иначе
    2.77
     jinak
    2.58
    Activations Density 0.909%

    No Known Activations