© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2669
    Prev
    Next
    INDEX
    Explanations

    references to film titles and their associated production details

    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
    +0.31
    1.4%
    382
    +0.14
    0.6%
    2019
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.31
    0.10
    2019
    +0.14
    0.09
    2034
    +0.13
    0.09
    Negative Logits
    <bos>
    -3.67
    /**
    -1.05
    <?
    -0.92
    /*
    -0.91
     AssemblyCompany
    -0.90
    ⓧ
    -0.87
    <?
    -0.79
    
    -0.77
     esternos
    -0.75
    Panamoan
    -0.72
    POSITIVE LOGITS
     maneu
    1.06
     Juf
    0.97
     Keny
    0.94
     disgra
    0.88
     Khart
    0.86
     accla
    0.86
     Minang
    0.86
     practition
    0.85
     volunte
    0.84
     épu
    0.82
    Activations Density 0.697%

    No Known Activations