© 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. 4513
    Prev
    Next
    INDEX
    Explanations

    references to the name "Christ."

    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
    +0.19
    1.1%
    950
    +0.15
    0.9%
    1805
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    950
    +0.19
    0.03
    1575
    +0.15
    0.02
    1097
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.52
    UrlResolution
    -0.75
    HideFlags
    -0.70
     vol
    -0.68
    GEBURTSDATUM
    -0.68
    HasForeignKey
    -0.67
    DeleteBehavior
    -0.66
    الإنجليزية
    -0.65
    MigrationBuilder
    -0.65
    Đăng
    -0.65
    POSITIVE LOGITS
     Juf
    1.58
     affor
    1.57
     Khart
    1.55
     strick
    1.52
     fta
    1.51
     accla
    1.50
     maneu
    1.49
     Augu
    1.48
     unlaw
    1.48
     inev
    1.47
    Activations Density 0.024%

    No Known Activations