© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1378
    Prev
    Next
    INDEX
    Explanations

    references to tight ends in football

    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
    +0.15
    0.6%
    1842
    +0.13
    0.5%
    581
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.15
    0.04
    1905
    +0.13
    0.03
    1842
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.82
     intersper
    -1.09
     encomp
    -0.80
     disbur
    -0.78
     endow
    -0.77
     gratify
    -0.72
    /***
    -0.70
     sogget
    -0.68
     overcrow
    -0.68
    
    -0.68
    POSITIVE LOGITS
     Universitaria
    0.59
     Señora
    0.56
     height
    0.53
    UIFont
    0.51
    setGravity
    0.51
     towering
    0.49
     Universitario
    0.48
    JTextArea
    0.48
     negru
    0.48
     tallest
    0.48
    Activations Density 0.174%

    No Known Activations