© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1667
    Prev
    Next
    INDEX
    Explanations

    references to prayer and religious customs

    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
    453
    +0.19
    0.7%
    50
    +0.17
    0.7%
    1842
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1284
    +0.19
    0.03
    1120
    +0.17
    0.01
    43
    +0.17
    0.03
    Negative Logits
    <bos>
    -2.06
    ⓧ
    -1.11
    <?
    -0.84
    Restaurante
    -0.81
    glPushMatrix
    -0.80
    Endereço
    -0.78
    Gost
    -0.78
    restaurante
    -0.77
    toMatch
    -0.77
    Neste
    -0.76
    POSITIVE LOGITS
     wien
    2.58
     stockholm
    2.55
     emphat
    2.51
     strick
    2.42
     aen
    2.34
     fta
    2.34
     bordeaux
    2.33
     affor
    2.32
     accla
    2.32
     effe
    2.32
    Activations Density 0.070%

    No Known Activations