© 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. 2095
    Prev
    Next
    INDEX
    Explanations

    descriptions of events related to large public gatherings or community activities

    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
    964
    +0.10
    0.3%
    946
    +0.09
    0.3%
    1804
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    222
    +0.10
    0.05
    81
    +0.09
    0.03
    946
    +0.08
    0.05
    Negative Logits
     vola
    -0.79
     vernac
    -0.69
     liev
    -0.68
     utop
    -0.65
     sement
    -0.65
     intest
    -0.63
     marte
    -0.63
     ananas
    -0.62
     sord
    -0.62
     asma
    -0.61
    POSITIVE LOGITS
     crowding
    0.57
     converging
    0.54
     churchyard
    0.53
     converged
    0.51
     throng
    0.50
     gathered
    0.49
     Shakspeare
    0.49
     converge
    0.49
     couverte
    0.48
     Ecclesiastical
    0.47
    Activations Density 0.448%

    No Known Activations