© 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. 1276
    Prev
    Next
    INDEX
    Explanations

    conversational phrases indicating familiarity or rapport between speakers

    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
    +0.33
    1.4%
    2034
    +0.10
    0.4%
    1741
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.33
    0.03
    1097
    +0.10
    0.03
    946
    +0.08
    0.02
    Negative Logits
    <bos>
    -2.29
    <?
    -0.98
    /***
    -0.91
    ⓧ
    -0.87
    <?
    -0.87
    /**
    -0.84
    
    -0.84
    /*
    -0.76
    vece
    -0.72
    Transkript
    -0.72
    POSITIVE LOGITS
     maneu
    0.70
     soulign
    0.59
     véhic
    0.57
     negru
    0.51
    pylab
    0.50
    setupUi
    0.50
     prêts
    0.49
     stickied
    0.49
     préoccup
    0.49
     réunis
    0.49
    Activations Density 0.107%

    No Known Activations