© 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. 3069
    Prev
    Next
    INDEX
    Explanations

    elements related to communication and connection

    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
     ourselves
    -0.97
    Our
    -0.89
    We
    -0.82
    我们的
    -0.78
     Our
    -0.76
     our
    -0.76
     våra
    -0.70
     наш
    -0.70
     ours
    -0.70
     nosso
    -0.70
    POSITIVE LOGITS
     kasarigan
    0.74
     miniaturka
    0.71
    ContentLoaded
    0.68
     AssemblyTitle
    0.65
    balleur
    0.65
    ஧
    0.63
     kapture
    0.63
     ſuo
    0.61
    ஬
    0.61
    InjectAttribute
    0.61
    Activations Density 0.453%

    No Known Activations