© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1061
    Prev
    Next
    INDEX
    Explanations

    numerical data in various formats

    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
    出版年
    -0.74
    %")
    -0.71
    ftagPool
    -0.68
    TagMode
    -0.67
     combineReducers
    -0.65
     ainfi
    -0.65
     provisoire
    -0.64
     Elin
    -0.64
     AspNetCore
    -0.64
    %=
    -0.63
    POSITIVE LOGITS
     sch
    0.67
    0
    0.66
    }{*}{
    0.61
     U
    0.60
    httphttps
    0.59
    ouille
    0.58
    HAPPY
    0.56
     Big
    0.56
     imp
    0.55
     Gu
    0.55
    Activations Density 0.366%

    No Known Activations