© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56231
    Prev
    Next
    INDEX
    Explanations

    instances of code structure or syntax, particularly focusing on object and variable definitions, comparisons, and data assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.69
    IVEREF
    -0.63
    Naissance
    -0.53
    клопе
    -0.51
     erle
    -0.50
    NÍ
    -0.50
     torno
    -0.49
    Assemblée
    -0.49
    دانشنامهٔ
    -0.49
    agen
    -0.48
    POSITIVE LOGITS
     saling
    0.69
    お互
    0.62
    حوالہ
    0.59
     umane
    0.58
     intptr
    0.57
    yntaxException
    0.56
     elkaar
    0.55
     juntos
    0.54
    mutual
    0.54
    Portale
    0.53
    Activations Density 0.281%

    No Known Activations