© 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. 16-GEMMASCOPE-RES-16K
    11. 9486
    Prev
    Next
    INDEX
    Explanations

    a significant decline in approval ratings

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

    Numbers followed by calculations

    np_acts-logits-general · gemini-2.0-flash

    least intelligent or worst outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.52
     informée
    -0.50
    amazonaws
    -0.50
    Gön
    -0.49
     estimés
    -0.48
     AspNetCore
    -0.47
    Enllaços
    -0.47
    RTDA
    -0.47
     gefe
    -0.46
    adering
    -0.45
    POSITIVE LOGITS
     worse
    1.27
     Worse
    1.21
     worst
    1.20
    Worse
    1.18
    Worst
    1.17
    worst
    1.14
     horrible
    1.14
     Worst
    1.14
     dismal
    1.12
     peggio
    1.12
    Activations Density 0.630%

    No Known Activations