© 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. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1761
    Prev
    Next
    INDEX
    Explanations

    references to the term "layout" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    169
    +0.20
    1.1%
    1092
    +0.17
    0.9%
    161
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1092
    +0.20
    0.02
    370
    +0.17
    0.02
    169
    +0.16
    0.02
    Negative Logits
    <bos>
    -1.50
     acred
    -0.80
    <?
    -0.78
    ⓧ
    -0.74
    Solución
    -0.73
     anzi
    -0.71
    uxxxx
    -0.71
    ///**
    -0.70
     himo
    -0.69
    Argumento
    -0.68
    POSITIVE LOGITS
     layout
    1.46
     Layout
    1.42
    layout
    1.35
     layouts
    1.35
     LAYOUT
    1.34
    Layout
    1.27
    LAYOUT
    1.09
    Layouts
    0.98
    layouts
    0.94
     tupperware
    0.91
    Activations Density 0.106%

    No Known Activations