© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2570
    Prev
    Next
    INDEX
    Explanations

    instances of the concept of pairing or coupling

    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%
    1892
    +0.12
    0.5%
    1387
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1892
    +0.19
    0.04
    223
    +0.12
    0.04
    1244
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.20
    <?
    -0.68
    WriteHeader
    -0.65
     bor
    -0.61
    /***
    -0.60
    //@
    -0.58
    #
    -0.58
     continue
    -0.57
     have
    -0.57
    Пото
    -0.57
    POSITIVE LOGITS
     impra
    1.68
     stockholm
    1.64
     maneu
    1.64
     aen
    1.60
     fta
    1.58
     thut
    1.58
     fortn
    1.56
     increa
    1.56
     hentai
    1.52
     milf
    1.52
    Activations Density 0.204%

    No Known Activations