© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4194
    Prev
    Next
    INDEX
    Explanations

    HTML and coding structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensement
    -0.53
    RefNanny
    -0.52
    ьаж
    -0.51
    lccn
    -0.49
     touristes
    -0.48
     betweenstory
    -0.48
    RenderAtEndOf
    -0.48
    Tikang
    -0.48
    IUrlHelper
    -0.47
    NewUrlParser
    -0.47
    POSITIVE LOGITS
     column
    0.64
    DataColumn
    0.61
     Column
    0.61
    ListItemIcon
    0.59
    Column
    0.57
     getWidth
    0.57
     DataTypes
    0.57
    AnchorStyles
    0.55
     vực
    0.55
    ξεις
    0.55
    Activations Density 0.099%

    No Known Activations