© 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. 6033
    Prev
    Next
    INDEX
    Explanations

    legal and medical terms related to financial transactions

    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
    1842
    +0.20
    0.6%
    198
    +0.15
    0.4%
    1177
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.20
    0.06
    198
    +0.15
    0.06
    1519
    +0.12
    0.05
    Negative Logits
     fraiche
    -0.65
    GEBURTSDATUM
    -0.59
    HttpDelete
    -0.55
    MLLoader
    -0.54
    ViewFeatures
    -0.53
    Geplaatst
    -0.53
     pageNum
    -0.53
    emples
    -0.51
     resultMap
    -0.50
    TestBed
    -0.50
    POSITIVE LOGITS
     Ueb
    0.62
     naer
    0.61
     saar
    0.61
     seiz
    0.61
     simpson
    0.60
     saad
    0.59
     Augu
    0.57
     bénéficiaire
    0.56
     goutte
    0.56
     lii
    0.56
    Activations Density 0.604%

    No Known Activations