© 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. 24-GEMMASCOPE-RES-16K
    11. 1505
    Prev
    Next
    INDEX
    Explanations

    terms related to data or encoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    French adverbs of intensity

    np_acts-logits-general · gemini-2.0-flash

    French intensifiers and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.55
    ItemBackground
    -0.54
    ⓧ
    -0.54
    PhysRev
    -0.53
     specchio
    -0.53
    cagon
    -0.51
    Rüyada
    -0.50
    期刊论文
    -0.49
    EndGlobalSection
    -0.49
    racuda
    -0.49
    POSITIVE LOGITS
     contest
    0.53
    出版年
    0.53
     bless
    0.52
    riwal
    0.50
     lour
    0.48
    PTION
    0.47
     caf
    0.47
     Scand
    0.46
    trop
    0.46
     catast
    0.45
    Activations Density 0.105%

    No Known Activations