© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 10870
    Prev
    Next
    INDEX
    Explanations

    references to specific countries or geopolitical terms

    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
    50
    +0.14
    0.5%
    1177
    +0.13
    0.4%
    381
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1965
    +0.14
    0.10
    1919
    +0.13
    0.09
    1177
    +0.12
    0.05
    Negative Logits
     palab
    -1.18
     ananas
    -1.17
     utop
    -1.14
     augus
    -1.13
     moza
    -1.13
     polig
    -1.12
     ciment
    -1.10
     poliester
    -1.10
     masaj
    -1.09
     marte
    -1.09
    POSITIVE LOGITS
     unwarran
    0.75
     has
    0.72
     didn
    0.69
     had
    0.67
     took
    0.65
     unspeak
    0.64
     won
    0.62
     is
    0.62
     bowiem
    0.62
     was
    0.61
    Activations Density 0.857%

    No Known Activations