© 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. 1376
    Prev
    Next
    INDEX
    Explanations

    references to military operations and equipment

    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
    +0.26
    1.0%
    1177
    +0.14
    0.5%
    394
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    906
    +0.26
    0.00
    775
    +0.14
    0.05
    1177
    +0.12
    0.01
    Negative Logits
    <bos>
    -2.69
    makeText
    -0.76
    ErrorListener
    -0.74
    invokeLater
    -0.73
    ganu
    -0.70
     ProtoMessage
    -0.70
    styleType
    -0.69
    irical
    -0.68
    /*
    -0.68
    DoubleQuotes
    -0.67
    POSITIVE LOGITS
     maneu
    2.09
     inev
    1.89
     affor
    1.88
     Juf
    1.86
     shenan
    1.85
     accla
    1.82
     disagre
    1.82
     resear
    1.79
     increa
    1.79
     reluct
    1.77
    Activations Density 0.581%

    No Known Activations