© 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. 1479
    Prev
    Next
    INDEX
    Explanations

    terms related to retro or nostalgia

    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
    1757
    +0.16
    0.9%
    1124
    +0.14
    0.7%
    545
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.16
    0.03
    1896
    +0.14
    0.02
    757
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.09
    ⓧ
    -0.74
    /**
    -0.69
    /*
    -0.68
     reele
    -0.62
    <?
    -0.62
    <?
    -0.61
    дивиду
    -0.57
     deposited
    -0.54
    aspectj
    -0.54
    POSITIVE LOGITS
     rétro
    1.31
     Retro
    1.21
    Retro
    1.17
    retro
    1.10
     retro
    1.08
     soigne
    1.03
     aperçu
    0.91
     Traité
    0.89
     exé
    0.89
     héro
    0.89
    Activations Density 0.163%

    No Known Activations