© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 7936
    Prev
    Next
    INDEX
    Explanations

    family-related names and ancestry information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstrumentedTest
    -0.50
    -------
    -0.50
     Psicología
    -0.46
     collè
    -0.45
    Geplaatst
    -0.44
     immobilier
    -0.43
     acrílico
    -0.43
     sintético
    -0.42
     intptr
    -0.42
    Judi
    -0.42
    POSITIVE LOGITS
     Maude
    0.63
     Bessie
    0.62
     Pearl
    0.62
     Annie
    0.61
     Minnie
    0.61
     Mabel
    0.60
     Ida
    0.57
     Ethel
    0.57
     Ruby
    0.56
    Annie
    0.55
    Activations Density 0.344%

    No Known Activations