© 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. 2-GEMMASCOPE-RES-16K
    11. 4342
    Prev
    Next
    INDEX
    Explanations

    references to the University of Texas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.56
    ifikationer
    -0.50
    seamnă
    -0.44
    ंदीखरीदारी
    -0.41
    /*
    -0.40
     Pria
    -0.39
    optionalTypeArgs
    -0.39
     CanadaChoose
    -0.39
     himo
    -0.38
    Bronnen
    -0.37
    POSITIVE LOGITS
    ut
    2.27
    UT
    2.22
     ut
    2.02
    uts
    1.95
     UT
    1.92
     Ut
    1.84
    ute
    1.81
    Ut
    1.70
    uta
    1.66
    utes
    1.63
    Activations Density 0.349%

    No Known Activations