© 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. 1622
    Prev
    Next
    INDEX
    Explanations

    statistical terms related to variability or standard deviation

    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
    1671
    +0.16
    0.8%
    568
    +0.13
    0.7%
    1492
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.16
    0.02
    1741
    +0.13
    0.00
    395
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.74
    ल्क
    -0.59
    насе
    -0.57
    Література
    -0.57
    جغرافيا
    -0.56
    Pens
    -0.55
    
    -0.55
     ujedno
    -0.54
     atrav
    -0.54
     treat
    -0.53
    POSITIVE LOGITS
     ±
    1.05
     (±
    1.05
     Czechos
    1.01
     Sén
    0.99
     Chapitre
    0.96
     bourgeo
    0.96
     Traité
    0.94
     ?...
    0.92
     chèvre
    0.92
     italia
    0.92
    Activations Density 0.138%

    No Known Activations