© 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. 293
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate doubt or uncertainty

    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
    +0.21
    0.8%
    1363
    +0.11
    0.4%
    991
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    991
    +0.21
    0.04
    1363
    +0.11
    0.04
    1482
    +0.10
    0.04
    Negative Logits
    <bos>
    -1.70
    /**
    -0.71
    
    -0.70
     intersper
    -0.66
    ⓧ
    -0.66
    /***
    -0.64
     strove
    -0.59
    /*
    -0.58
    ///**
    -0.56
     clutched
    -0.53
    POSITIVE LOGITS
     signora
    1.17
     fidanz
    1.09
     toscana
    0.99
     cammin
    0.99
     chèvre
    0.97
     ristor
    0.97
     cioc
    0.96
     jawa
    0.95
     papà
    0.94
     Bárbara
    0.94
    Activations Density 0.133%

    No Known Activations