© 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. 19
    Prev
    Next
    INDEX
    Explanations

    terms related to trade and services

    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
    +0.27
    0.9%
    856
    +0.09
    0.3%
    1288
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    955
    +0.27
    0.07
    1314
    +0.09
    0.07
    1633
    +0.08
    0.07
    Negative Logits
    <bos>
    -3.02
    Autoritní
    -1.09
    SourceChecksum
    -0.98
    SequentialGroup
    -0.86
    Билгалдахарш
    -0.75
     Мексичка
    -0.75
     snippetHide
    -0.73
    CreateMap
    -0.70
    ///**
    -0.69
    SpringBootTest
    -0.68
    POSITIVE LOGITS
     jaya
    1.00
     lele
    0.98
     maske
    0.96
     saar
    0.95
     chevrolet
    0.95
     xdrive
    0.94
     chrysler
    0.93
     bordeaux
    0.93
     affor
    0.91
     riva
    0.90
    Activations Density 0.469%

    No Known Activations