© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1318
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and"

    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
    50
    +0.35
    1.7%
    2019
    +0.12
    0.5%
    1842
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.35
    0.12
    1892
    +0.12
    0.11
    1520
    +0.10
    0.11
    Negative Logits
    <bos>
    -3.13
     referenties
    -0.90
    ksikon
    -0.79
     kasarigan
    -0.78
     AssemblyCompany
    -0.76
    <?
    -0.75
    forChild
    -0.75
    
    
    -0.75
    <!--[
    -0.75
    bitat
    -0.74
    POSITIVE LOGITS
     increa
    2.29
     reluct
    2.19
     affor
    2.17
     maneu
    2.16
     guarante
    2.16
     disagre
    2.13
     inev
    2.13
     impra
    2.12
     accla
    2.03
     shenan
    1.99
    Activations Density 0.953%

    No Known Activations