© 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. 4694
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes, restrictions, or violations

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

    followed by suffixes (-ating, -ize, -tion, -amos, etc.)

    np_acts-logits-general · gemini-2.0-flash

    assign, invalidate, select, scrutinize, associate, demonstrate, modify, recognize

    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
    Personendaten
    -0.58
    <eos>
    -0.57
    argli
    -0.57
    DataSnapshot
    -0.56
    في
    -0.55
    tetten
    -0.53
     einde
    -0.52
    $_['
    -0.52
    ávajú
    -0.51
     Edwards
    -0.50
    POSITIVE LOGITS
     noDo
    0.71
     חיצוניים
    0.69
     متعلقه
    0.65
     typelib
    0.65
     photolibrary
    0.64
    gdx
    0.64
    riwal
    0.64
    ztály
    0.63
     marinho
    0.63
    jemah
    0.61
    Activations Density 0.255%

    No Known Activations