© 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. 7426
    Prev
    Next
    INDEX
    Explanations

    government-related terms and actions

    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
    1499
    +0.11
    0.3%
    1177
    +0.11
    0.3%
    764
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.11
    0.09
    1048
    +0.11
    0.03
    583
    +0.09
    0.04
    Negative Logits
     peppa
    -0.97
     nutella
    -0.97
     jacques
    -0.94
     soigne
    -0.89
     répon
    -0.88
     obé
    -0.84
     prétend
    -0.83
     noel
    -0.83
     yves
    -0.82
     trouva
    -0.80
    POSITIVE LOGITS
     officially
    0.65
     formally
    0.64
    Conclusión
    0.55
    ypeł
    0.54
    (!_
    0.53
    officially
    0.53
     issued
    0.52
    ==""){
    0.52
     crackdown
    0.51
     antitrust
    0.51
    Activations Density 0.654%

    No Known Activations