© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15841
    Prev
    Next
    INDEX
    Explanations

    modals and verbs indicating potential actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wydaje
    -0.61
     usually
    -0.60
    usually
    -0.57
     schein
    -0.57
    Seems
    -0.57
     dụ
    -0.56
    often
    -0.55
     often
    -0.55
     umumnya
    -0.55
     generally
    -0.54
    POSITIVE LOGITS
     someday
    0.99
     soon
    0.97
    GEBURTSDATUM
    0.92
    soon
    0.80
     Soon
    0.75
    Soon
    0.75
     bientôt
    0.75
     Eventually
    0.74
    Eventually
    0.74
     eventually
    0.74
    Activations Density 0.311%

    No Known Activations