© 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. 4-GEMMASCOPE-RES-16K
    6. 15421
    Prev
    Next
    INDEX
    Explanations

    closing braces and their surrounding syntax in code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "):
    
    -1.16
    تقاوى
    -1.11
    LookAnd
    -1.11
    .",
    
    -1.09
    ViewFeatures
    -1.09
     فريبيس
    -1.08
    )";
    
    -1.06
    Personensuche
    -1.04
    `,
    
    -1.02
    WriteTagHelper
    -1.02
    POSITIVE LOGITS
    endphp
    0.89
    partiet
    0.66
     virgen
    0.59
    shund
    0.58
     botanique
    0.57
     dormitorios
    0.56
     iglesias
    0.56
     ?>
    0.56
    ielli
    0.55
     comunicar
    0.55
    Activations Density 0.316%

    No Known Activations