© 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. 5104
    Prev
    Next
    INDEX
    Explanations

    legal terms and actions related to court proceedings and motions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    0.9%
    453
    +0.17
    0.6%
    1150
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.23
    0.06
    1553
    +0.17
    0.05
    946
    +0.15
    0.04
    Negative Logits
    <bos>
    -2.97
    ///**
    -0.74
    /***
    -0.73
    fputs
    -0.68
    ⓧ
    -0.68
    verifyException
    -0.64
    agosto
    -0.64
    afterEach
    -0.60
     ldc
    -0.59
    awt
    -0.59
    POSITIVE LOGITS
     stockholm
    1.60
     Minang
    1.45
     toledo
    1.43
     munich
    1.43
     frankfurt
    1.43
     panama
    1.41
     bangkok
    1.40
     beverly
    1.40
     tucson
    1.37
     venice
    1.30
    Activations Density 0.464%

    No Known Activations