© 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. 18-GEMMASCOPE-RES-16K
    11. 9017
    Prev
    Next
    INDEX
    Explanations

    words related to legal decisions or rulings

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

    Punctuation, abbreviations, and equation markers after text

    np_acts-logits-general · gemini-2.0-flash

    consecutive or successive events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.69
     veckor
    -0.64
     متعلقه
    -0.63
    expandindo
    -0.62
    原始内容存档于
    -0.60
     المعيارى
    -0.59
    ChildScrollView
    -0.59
     lieto
    -0.58
     daily
    -0.58
     فريبيس
    -0.56
    POSITIVE LOGITS
    المناصب
    0.65
    IntoConstraints
    0.62
    DeleteBehavior
    0.55
     ensuing
    0.54
     consecutive
    0.53
     momentarily
    0.52
    styleable
    0.52
     successive
    0.51
    quickly
    0.50
    Ensuite
    0.48
    Activations Density 0.126%

    No Known Activations