© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6490
    Prev
    Next
    INDEX
    Explanations

    mentions of specific religious terms and activities in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    946
    +0.10
    0.3%
    1013
    +0.10
    0.3%
    509
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.10
    0.02
    509
    +0.10
    0.06
    37
    +0.10
    0.03
    Negative Logits
     lapto
    -0.87
     affez
    -0.86
     pylab
    -0.82
     pymysql
    -0.79
     sappi
    -0.76
     zipfile
    -0.71
     disreg
    -0.71
     soggior
    -0.70
     heapq
    -0.69
     jaya
    -0.68
    POSITIVE LOGITS
     church
    0.61
     Church
    0.57
     community
    0.53
     Community
    0.52
     churches
    0.52
     religious
    0.51
     Iglesias
    0.50
    church
    0.46
     Religious
    0.45
     Domínguez
    0.44
    Activations Density 0.686%

    No Known Activations