© 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. 16-GEMMASCOPE-RES-16K
    6. 3697
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements, particularly in programming or markup language structures

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

    Code snippets with comments

    np_acts-logits-general · gemini-2.0-flash

    before, Si-, _{, mid

    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
     Shaksp
    -0.67
    Hochspringen
    -0.63
    HasAnnotation
    -0.60
    期刊论文
    -0.59
     pylint
    -0.59
    хьтан
    -0.58
    BagConstraints
    -0.57
     MZ
    -0.56
     brosse
    -0.55
    তথ্যসূত্র
    -0.54
    POSITIVE LOGITS
    WaitGroup
    0.55
     nahilalakip
    0.50
     للاسماء
    0.50
    inco
    0.48
     Par
    0.46
     trajets
    0.46
    логе
    0.45
    ʔ
    0.44
    hamdu
    0.44
    Adrien
    0.44
    Activations Density 0.059%

    No Known Activations