© 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. 436
    Prev
    Next
    INDEX
    Explanations

    references to media content, particularly movies, drugs, music, and digital translations

    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
    +0.28
    1.2%
    1842
    +0.16
    0.7%
    1870
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.28
    0.08
    1842
    +0.16
    0.06
    908
    +0.13
    0.06
    Negative Logits
    <bos>
    -2.79
    
    -0.97
    ⓧ
    -0.97
    /***
    -0.89
    /**
    -0.88
    /*!
    -0.71
     /**
    -0.70
    <?
    -0.70
    żdy
    -0.69
    /*
    -0.68
    POSITIVE LOGITS
     riva
    0.86
     rancho
    0.85
     maroc
    0.81
     riviera
    0.79
     prado
    0.78
     eiffel
    0.78
     tucson
    0.77
     paradiso
    0.76
     croce
    0.75
     soldati
    0.74
    Activations Density 1.188%

    No Known Activations