© 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. 8251
    Prev
    Next
    INDEX
    Explanations

    sections and figures in academic or technical documents

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

    Text referring to figures, equations, or tables

    np_acts-logits-general · gemini-2.0-flash

    column or inset shows

    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
    ReusableCell
    -0.81
    SpringBootTest
    -0.73
    IUrlHelper
    -0.73
     EconPapers
    -0.72
     NSCoder
    -0.70
    __(/*!
    -0.69
    WithMany
    -0.68
    principalColumn
    -0.68
    XmlAccessType
    -0.67
    twimg
    -0.67
    POSITIVE LOGITS
     represents
    0.81
     provides
    0.79
     is
    0.79
     indicates
    0.66
     serves
    0.66
    则是
    0.66
     relates
    0.66
     merupakan
    0.65
     natomiast
    0.61
     describes
    0.61
    Activations Density 0.457%

    No Known Activations