© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4236
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the availability or current status of products or treatments

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

    "Currently" followed by a comma or other word

    np_acts-logits-general · gemini-2.0-flash

    Currently

    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
     previously
    -0.88
     autrefois
    -0.86
    previously
    -0.82
     vroeger
    -0.78
     künftig
    -0.78
     kiedyś
    -0.78
     recently
    -0.77
     eventually
    -0.76
     previous
    -0.75
     henceforth
    -0.75
    POSITIVE LOGITS
    为止
    0.96
    TestingModule
    0.81
    varande
    0.72
    CURRENT
    0.71
     EconPapers
    0.70
    WebVitals
    0.68
    værende
    0.68
    шні
    0.61
    tvguidetime
    0.59
     CURRENT
    0.59
    Activations Density 0.165%

    No Known Activations