© 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. 8418
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and structure in technical documents

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

    LaTeX math mode or equations

    np_acts-logits-general · gemini-2.0-flash

    Nr. or similar numbering

    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
     насељу
    -0.56
     CYTHON
    -0.52
    <code>
    -0.51
     &
    -0.47
    ⓧ
    -0.45
    OneToOne
    -0.45
    <strong>
    -0.44
    instantiate
    -0.43
    Twin
    -0.43
     Twin
    -0.42
    POSITIVE LOGITS
    __':
    0.93
    存于互联网档案馆
    0.80
    moiselle
    0.79
    PerformLayout
    0.76
     AttributeSet
    0.73
    <()>
    0.73
    .}~\
    0.72
    AsUp
    0.71
     ujednoznacz
    0.71
     themſelves
    0.70
    Activations Density 1.146%

    No Known Activations