© 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. 3860
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence structures

    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
    +0.22
    1.0%
    382
    +0.21
    1.0%
    1150
    +0.19
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.22
    0.19
    2034
    +0.21
    0.16
    2019
    +0.19
    0.15
    Negative Logits
    <bos>
    -3.18
    ⓧ
    -1.11
    /**
    -0.97
    <?
    -0.96
    
    -0.88
    /*
    -0.87
     springfox
    -0.81
    InputBorder
    -0.79
     AssemblyCompany
    -0.78
    /***
    -0.77
    POSITIVE LOGITS
     maneu
    1.27
     fortn
    1.13
     accla
    1.11
     increa
    1.05
     uninten
    1.04
     disgra
    1.03
     reluct
    1.03
     Juf
    1.01
     volunte
    1.00
     véhic
    0.99
    Activations Density 1.266%

    No Known Activations