© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14368
    Prev
    Next
    INDEX
    Explanations

    references to specific governmental buildings or institutions

    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
    1870
    +0.13
    0.4%
    1187
    +0.13
    0.4%
    629
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.13
    0.03
    517
    +0.13
    0.02
    1861
    +0.12
    0.03
    Negative Logits
     encomp
    -0.79
     fuf
    -0.76
     shewn
    -0.75
     scrat
    -0.73
     Quoi
    -0.72
     fays
    -0.72
     apprehen
    -0.72
     guarante
    -0.71
     greate
    -0.71
     increa
    -0.71
    POSITIVE LOGITS
     Parliament
    1.22
     parliament
    1.21
    Parliament
    1.17
     parliamentary
    0.95
    parliament
    0.94
     Parliamentary
    0.91
     MP
    0.80
     MPs
    0.79
     Parlament
    0.77
    MP
    0.71
    Activations Density 0.075%

    No Known Activations