© 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. 4394
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Led"

    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
    1.3%
    1271
    +0.15
    0.8%
    1974
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1271
    +0.22
    0.04
    1942
    +0.15
    0.03
    1974
    +0.14
    0.03
    Negative Logits
    <bos>
    -2.62
    print
    -0.57
    幕
    -0.55
                                   
    -0.55
     recover
    -0.55
    /*++
    -0.53
    },[])
    -0.53
    容
    -0.53
     download
    -0.53
    山
    -0.53
    POSITIVE LOGITS
     increa
    1.52
     maneu
    1.50
     affor
    1.49
     emphat
    1.40
     shenan
    1.39
     inev
    1.38
     Minang
    1.37
     impra
    1.36
     accla
    1.32
     reluct
    1.32
    Activations Density 0.039%

    No Known Activations