© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4644
    Prev
    Next
    INDEX
    Explanations

    legal and procedural terms related to judicial guidelines and rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gainera
    -0.56
    googleapis
    -0.54
    Datuak
    -0.53
     chi̍t
    -0.50
    expandindo
    -0.49
     trust
    -0.47
    rinfo
    -0.47
     estimés
    -0.45
    TypedDataSet
    -0.45
     Advantage
    -0.45
    POSITIVE LOGITS
     subsection
    0.82
     paragraph
    0.77
     subsections
    0.76
     section
    0.75
     sections
    0.73
     Section
    0.71
     Sections
    0.70
     paragraphs
    0.69
    webElementXpaths
    0.69
     Subsection
    0.68
    Activations Density 0.398%

    No Known Activations