© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 16150
    Prev
    Next
    INDEX
    Explanations

    mentions of economic terms, particularly related to international trade and economic partnerships

    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
    674
    +0.09
    0.3%
    198
    +0.09
    0.3%
    1370
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.09
    0.03
    198
    +0.09
    0.03
    1363
    +0.09
    0.03
    Negative Logits
     stockholm
    -1.11
     wien
    -1.09
     exem
    -1.06
     madonna
    -1.03
     myn
    -1.02
     pessi
    -1.01
     unden
    -1.00
     oner
    -1.00
     inder
    -0.99
     calvin
    -0.99
    POSITIVE LOGITS
    <bos>
    0.96
     للمعارف
    0.56
     powi
    0.55
    Rozm
    0.52
     setTotal
    0.51
     pinulongan
    0.50
     versions
    0.49
    日在
    0.48
    日至
    0.48
    Ży
    0.48
    Activations Density 0.210%

    No Known Activations