© 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. 3-GEMMASCOPE-RES-16K
    11. 9665
    Prev
    Next
    INDEX
    Explanations

    image attributes and thread-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pubblic
    -0.45
     Utama
    -0.44
    anthene
    -0.42
     pilar
    -0.41
     conden
    -0.40
     šal
    -0.40
     valmist
    -0.40
     fabric
    -0.38
     ferons
    -0.37
     excavations
    -0.36
    POSITIVE LOGITS
     DJ
    1.05
    DJ
    0.98
     dj
    0.91
     Dj
    0.90
    dj
    0.88
     django
    0.87
    Dj
    0.83
     DJs
    0.69
    httphttps
    0.62
    OGND
    0.59
    Activations Density 0.086%

    No Known Activations