© 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. 2430
    Prev
    Next
    INDEX
    Explanations

    references to government entities and their roles

    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
    +0.20
    0.7%
    1870
    +0.13
    0.5%
    678
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.20
    0.05
    1385
    +0.13
    0.07
    1531
    +0.13
    0.05
    Negative Logits
    <bos>
    -3.03
     initComponents
    -0.81
    rungsseite
    -0.80
    mergeFrom
    -0.78
    ValueGenerated
    -0.76
    HasIndex
    -0.75
    AnchorStyles
    -0.72
    nocache
    -0.72
    RenderAtEndOf
    -0.70
    IANGLES
    -0.69
    POSITIVE LOGITS
     Juf
    1.50
     Perci
    1.43
     Minang
    1.39
     sappi
    1.36
     Keny
    1.34
     Intere
    1.33
     Godt
    1.29
     unlaw
    1.26
     Simult
    1.23
     embodi
    1.22
    Activations Density 0.605%

    No Known Activations