© 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. 25-GEMMASCOPE-RES-16K
    11. 14958
    Prev
    Next
    INDEX
    Explanations

    terms related to modern architecture and its relationship to design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становника
    -0.60
    CloseOperation
    -0.57
     PyTuple
    -0.56
    期刊论文
    -0.54
    ReusableCell
    -0.54
     pageContext
    -0.53
     dibujado
    -0.53
    URLException
    -0.52
    rawDesc
    -0.52
    SequentialGroup
    -0.51
    POSITIVE LOGITS
     cub
    0.78
     Dada
    0.77
     Cub
    0.76
     Salvador
    0.72
     Kand
    0.68
     Picasso
    0.68
    Salvador
    0.68
     dada
    0.68
     Mond
    0.67
    Cub
    0.65
    Activations Density 0.268%

    No Known Activations