© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 2795
    Prev
    Next
    INDEX
    Explanations

    nouns and names of people or historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.39
     Wadsworth
    -0.37
    wake
    -0.37
    vac
    -0.34
    vas
    -0.34
     Vaz
    -0.34
     Vasco
    -0.33
    ûte
    -0.32
     Wak
    -0.32
     Vac
    -0.32
    POSITIVE LOGITS
     Will
    2.23
     Willi
    2.16
     Wil
    2.11
    Will
    2.09
    Wil
    2.02
    Willi
    2.00
    WILL
    1.98
     Willa
    1.86
     William
    1.86
    wil
    1.85
    Activations Density 0.857%

    No Known Activations