© 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. 8399
    Prev
    Next
    INDEX
    Explanations

    references to specific cases or conditions in technical or legal discussions

    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
    Continue
    -0.35
    today
    -0.32
     başlad
    -0.31
     enää
    -0.31
     jäl
    -0.30
     sää
    -0.30
     today
    -0.30
    Today
    -0.29
    .‏
    -0.29
    ¦
    -0.29
    POSITIVE LOGITS
     iſt
    0.82
     Bayesian
    0.79
     Cauchy
    0.78
     kasarigan
    0.77
     Dirichlet
    0.75
     vPvB
    0.75
     Lagrangian
    0.75
    niſſe
    0.75
     Theorems
    0.71
     lymphoid
    0.71
    Activations Density 4.009%

    No Known Activations