© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5232
    Prev
    Next
    INDEX
    Explanations

    mentions of specific ethnic groups and locations, particularly related to historical contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    251
    +0.16
    0.8%
    32
    +0.14
    0.7%
    1306
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.16
    0.06
    1741
    +0.14
    0.00
    690
    +0.12
    0.04
    Negative Logits
     vesel
    -0.69
     igra
    -0.69
     Betts
    -0.66
     pono
    -0.62
     vodi
    -0.59
     veliko
    -0.57
     pove
    -0.57
     vode
    -0.57
     manj
    -0.55
     krep
    -0.54
    POSITIVE LOGITS
     Maya
    1.02
    Maya
    0.99
     Guatem
    0.94
     Guatemala
    0.93
    Guatemala
    0.86
     Bén
    0.76
     maya
    0.73
     Mayan
    0.69
     TextFormField
    0.66
     Châ
    0.64
    Activations Density 0.563%

    No Known Activations