© 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. 13221
    Prev
    Next
    INDEX
    Explanations

    mathematical statements involving conditions and sets

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

    "For all" construction in mathematical text

    np_acts-logits-general · gemini-2.0-flash

    for all

    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
    存于互联网档案馆
    -0.65
     SqlDbType
    -0.63
     utafitiHapana
    -0.56
    ഠ
    -0.54
    StoryboardSegue
    -0.54
    يديا
    -0.54
     _("
    -0.53
     rasanya
    -0.52
     Normdatei
    -0.51
     Offisielt
    -0.49
    POSITIVE LOGITS
    :✨
    0.79
    HtmlAttribute
    0.65
    verifyException
    0.65
     <>",
    0.63
    awtextra
    0.62
     any
    0.61
     surla
    0.60
     belieb
    0.60
    richTextPanel
    0.58
     qualunque
    0.56
    Activations Density 0.816%

    No Known Activations