© 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. 3589
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases that highlight impressive views and cityscapes

    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
    1.1%
    906
    +0.17
    0.6%
    1385
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    906
    +0.29
    0.01
    1385
    +0.17
    0.04
    1013
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.07
    ⓧ
    -1.15
    <?
    -1.06
    /**
    -0.96
    
    -0.93
    /*
    -0.79
    <?
    -0.78
    /*++
    -0.72
    /***
    -0.70
    #
    -0.68
    POSITIVE LOGITS
     lamborghini
    1.35
     chrysler
    1.32
     gsx
    1.29
     swarovski
    1.28
     cytoplas
    1.25
     outlander
    1.24
     hentai
    1.24
     malheureux
    1.24
     casio
    1.22
     ufc
    1.21
    Activations Density 0.292%

    No Known Activations