© 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. 18-GEMMASCOPE-RES-16K
    11. 15483
    Prev
    Next
    INDEX
    Explanations

    phrases indicating improvement and motivation related to future actions

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

    future events or times

    np_acts-logits-general · gemini-2.0-flash

    next time or future

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.74
    vode
    -0.66
    
    -0.61
    MigrationBuilder
    -0.60
    WebServlet
    -0.60
    WriteBarrier
    -0.58
    IUrlHelper
    -0.57
     defaultstate
    -0.57
     useAppContext
    -0.56
    Personensuche
    -0.56
    POSITIVE LOGITS
     future
    2.50
     next
    2.33
    future
    2.19
    next
    2.06
    Future
    1.88
    下次
    1.83
    Next
    1.83
     Future
    1.82
     prochaine
    1.82
     Next
    1.78
    Activations Density 0.435%

    No Known Activations