© 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. 10-GEMMASCOPE-RES-16K
    11. 9216
    Prev
    Next
    INDEX
    Explanations

    French verbs related to obligation and necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themselves
    -0.44
     verkar
    -0.37
     Compound
    -0.36
     they
    -0.36
    stateProvider
    -0.35
     compounds
    -0.34
     proprement
    -0.34
     compound
    -0.33
     annen
    -0.33
     cose
    -0.33
    POSITIVE LOGITS
     myself
    1.09
    myself
    1.00
     my
    0.88
     Myself
    0.88
    Myself
    0.87
     myſelf
    0.79
     mijn
    0.71
     minhas
    0.70
     meinem
    0.69
    我的
    0.68
    Activations Density 2.416%

    No Known Activations