© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4856
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts and court-related language

    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
    +0.29
    1.1%
    1499
    +0.11
    0.4%
    1842
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.29
    0.08
    946
    +0.11
    0.05
    1842
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.60
    /***
    -0.83
     verra
    -0.71
     дописавши
    -0.64
    <!--
    -0.64
    fileprivate
    -0.61
    //});
    -0.59
    otheby
    -0.58
     dirait
    -0.58
    readAs
    -0.57
    POSITIVE LOGITS
     Minang
    1.15
     bandung
    1.05
     jaya
    1.01
     jawa
    0.94
     seoul
    0.92
     tucson
    0.91
     javier
    0.88
     santiago
    0.88
     softshell
    0.86
     jorge
    0.85
    Activations Density 0.718%

    No Known Activations