© 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. 2913
    Prev
    Next
    INDEX
    Explanations

    references to money and coal

    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
    +0.31
    1.1%
    184
    +0.09
    0.3%
    1510
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    638
    +0.31
    0.08
    1385
    +0.09
    0.09
    1978
    +0.08
    0.08
    Negative Logits
    <bos>
    -2.48
     autorytatywna
    -0.77
    ⓧ
    -0.72
    Geplaatst
    -0.70
    Билгалдахарш
    -0.69
    Referències
    -0.69
    TagMode
    -0.69
    <tfoot>
    -0.66
     bezeichneter
    -0.65
    Personendaten
    -0.64
    POSITIVE LOGITS
     silikon
    1.06
     seksi
    1.03
     maske
    0.99
     kafe
    0.98
     karton
    0.94
     saar
    0.92
     kristal
    0.92
     kasa
    0.91
     alip
    0.89
     benzin
    0.89
    Activations Density 0.904%

    No Known Activations