© 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. 15-GEMMASCOPE-RES-16K
    11. 7959
    Prev
    Next
    INDEX
    Explanations

    references to statistical methodologies and numerical data in research articles

    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
    expandindo
    -0.81
     ModelExpression
    -0.77
    ьаж
    -0.70
    Vidite
    -0.68
    Cursors
    -0.68
    sidemargin
    -0.68
    Rptr
    -0.66
    UnusedPrivate
    -0.66
    +#+#
    -0.66
    AccessorTable
    -0.65
    POSITIVE LOGITS
    ::::::::
    0.51
     humaines
    0.47
     supérieurs
    0.46
     sacré
    0.45
     inférieure
    0.45
    xase
    0.45
    antMatchers
    0.44
     frågan
    0.43
     direta
    0.43
    ícil
    0.42
    Activations Density 0.140%

    No Known Activations