© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3815
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly brackets and parentheses

    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
    +0.29
    1.4%
    1262
    +0.15
    0.7%
    605
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1262
    +0.29
    0.04
    900
    +0.15
    0.03
    605
    +0.10
    0.01
    Negative Logits
    <bos>
    -2.84
    ⓧ
    -0.99
    <?
    -0.96
    /**
    -0.79
    /*!
    -0.73
    /***
    -0.69
    
    -0.69
    contentLoaded
    -0.60
    /*
    -0.59
     /**
    -0.56
    POSITIVE LOGITS
     seksi
    0.80
     bandung
    0.80
     ''}
    0.79
    %")
    0.78
     [''],
    0.76
     kafe
    0.74
     uhr
    0.74
     ""}
    0.73
     balon
    0.72
     conster
    0.70
    Activations Density 0.065%

    No Known Activations