© 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. 58071
    Prev
    Next
    INDEX
    Explanations

    method and function calls related to database and XML operations

    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
    ValueStyle
    -0.66
    IUrlHelper
    -0.55
    RTLD
    -0.51
    GenerationType
    -0.49
    ----</
    -0.48
    لول
    -0.48
     jspb
    -0.47
     continuant
    -0.47
     Luk
    -0.46
     đoàn
    -0.46
    POSITIVE LOGITS
    ReusableCell
    0.81
    RenderAtEndOf
    0.72
     Italijani
    0.67
     Drapeau
    0.63
     Профиль
    0.59
    UrlResolution
    0.58
    yntaxException
    0.55
     PFA
    0.55
    躇
    0.55
     AssemblyCulture
    0.54
    Activations Density 0.139%

    No Known Activations