© 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. 12466
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical periods or specific centuries

    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
    1639
    +0.13
    0.4%
    1222
    +0.12
    0.4%
    1363
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1639
    +0.13
    0.02
    1856
    +0.12
    0.03
    1993
    +0.11
    0.02
    Negative Logits
     volon
    -0.55
    Dès
    -0.54
     ModelExpression
    -0.53
     Dès
    -0.52
     Lorsqu
    -0.52
     Marzo
    -0.51
     saluti
    -0.50
     Jusqu
    -0.50
     Altri
    -0.49
     parlano
    -0.49
    POSITIVE LOGITS
     century
    1.02
    century
    0.98
     CENTURY
    0.96
     Century
    0.95
    Century
    0.88
     Jahrhunderts
    0.72
     eeuw
    0.72
     siècle
    0.72
     Centuries
    0.71
     Jahrhundert
    0.69
    Activations Density 0.050%

    No Known Activations