© 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. 22-GEMMASCOPE-RES-16K
    11. 3211
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and expressions of desire or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding a verb of permission/obligation

    np_acts-logits-general · gemini-2.0-flash

    being, having, getting, choosing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ustimmung
    -0.54
     Straß
    -0.51
    Odkazy
    -0.51
     возь
    -0.50
     zrobi
    -0.50
     Agreg
    -0.50
     rispond
    -0.49
     uzyska
    -0.49
     нажмите
    -0.48
    ronom
    -0.48
    POSITIVE LOGITS
     being
    1.03
     having
    0.92
     Being
    0.91
    being
    0.89
    Being
    0.89
     BEING
    0.81
     getting
    0.79
     choosing
    0.76
     doing
    0.76
     selecting
    0.76
    Activations Density 0.071%

    No Known Activations