© 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. 4170
    Prev
    Next
    INDEX
    Explanations

    elements related to community dynamics and official recommendations

    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
    +0.30
    1.2%
    394
    +0.10
    0.4%
    1351
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.30
    0.09
    1224
    +0.10
    0.04
    304
    +0.08
    -0.03
    Negative Logits
    <bos>
    -3.02
    ///**
    -0.74
     AssemblyCompany
    -0.71
    //{
    -0.69
    पया
    -0.64
    /***
    -0.64
    מבר
    -0.63
    SPECTION
    -0.63
    /*
    -0.63
    TargetException
    -0.63
    POSITIVE LOGITS
     impra
    1.86
     reluct
    1.81
     increa
    1.78
     maneu
    1.77
     affor
    1.76
     accla
    1.75
     disagre
    1.74
     depic
    1.68
     inev
    1.67
     uninten
    1.64
    Activations Density 1.318%

    No Known Activations