© 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. 13385
    Prev
    Next
    INDEX
    Explanations

    dates and historical events related to political conventions, nominations, and expositions

    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
    674
    +0.14
    0.4%
    350
    +0.08
    0.2%
    1878
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.14
    0.03
    1295
    +0.08
    0.03
    1558
    +0.07
    0.03
    Negative Logits
     Rollo
    -0.57
     Schot
    -0.51
     Popp
    -0.49
     Sarm
    -0.48
     Juf
    -0.48
     Mathi
    -0.47
     Hez
    -0.47
     Timp
    -0.47
     Cornelia
    -0.47
     Khart
    -0.46
    POSITIVE LOGITS
     credere
    0.73
     vorrei
    0.70
    ihnachten
    0.67
     voglio
    0.67
     volete
    0.64
     avevo
    0.64
    <bos>
    0.63
     sento
    0.60
     affatto
    0.60
     pantal
    0.60
    Activations Density 0.077%

    No Known Activations