© 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. 8421
    Prev
    Next
    INDEX
    Explanations

    information related to specific chemical compounds and their biological effects

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

    Appears before brackets or Roman numerals

    np_acts-logits-general · gemini-2.0-flash

    radix lind AT- binding sh Control

    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
     الرياضيه
    -0.89
     مشين
    -0.87
     nakalista
    -0.82
    __((
    -0.82
    +#+#
    -0.81
     itſelf
    -0.79
    #+#
    -0.78
     Etrus
    -0.77
    endphp
    -0.76
     viewDidLoad
    -0.75
    POSITIVE LOGITS
     Rosenberg
    0.54
     T
    0.49
     Williams
    0.49
     Ab
    0.49
     Al
    0.47
    IUrlHelper
    0.47
     Dr
    0.47
     St
    0.46
     Mal
    0.46
     J
    0.45
    Activations Density 1.020%

    No Known Activations