© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8823
    Prev
    Next
    INDEX
    Explanations

    various nested structures in mathematical expressions or syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -1.42
    ()]);
    -1.13
     ―――――
    -1.10
     للاسماء
    -1.10
     kaarangay
    -1.10
     AssemblyVersion
    -1.08
    :✨
    -1.08
     doubtnut
    -1.06
     Roskov
    -1.04
     ویکی‌پدی
    -1.04
    POSITIVE LOGITS
    ’
    1.59
    '
    1.49
    <bos>
    1.03
     
    0.92
     to
    0.65
     due
    0.62
     of
    0.61
    enumi
    0.60
    ‘
    0.59
      
    0.59
    Activations Density 0.141%

    No Known Activations