© 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. 1673
    Prev
    Next
    INDEX
    Explanations

    references to religious texts and their impact

    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
    +0.19
    0.7%
    1978
    +0.19
    0.7%
    1967
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.19
    0.10
    1385
    +0.19
    0.08
    1987
    +0.17
    0.06
    Negative Logits
    <bos>
    -2.79
     Italijani
    -0.97
     Мексичка
    -0.97
     autorytatywna
    -0.93
    Autoritní
    -0.93
     kasarigan
    -0.86
     initComponents
    -0.84
    ⓧ
    -0.83
     Савезне
    -0.81
     disbur
    -0.79
    POSITIVE LOGITS
     marte
    0.97
     maroc
    0.96
     seksi
    0.89
     Meksi
    0.87
     miniatura
    0.85
     kafe
    0.83
     ados
    0.82
     ananas
    0.81
     silikon
    0.81
     kristal
    0.81
    Activations Density 0.723%

    No Known Activations