© 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. 6514
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events and political figures

    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
    2019
    +0.38
    1.3%
    1535
    +0.25
    0.9%
    304
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.38
    0.09
    1535
    +0.25
    0.07
    946
    +0.14
    0.06
    Negative Logits
     Darum
    -0.83
     explications
    -0.74
     Endlich
    -0.68
     Zwar
    -0.68
     tupperware
    -0.67
     bandai
    -0.66
     pensées
    -0.62
    Może
    -0.62
     offens
    -0.61
     DELLE
    -0.61
    POSITIVE LOGITS
    During
    0.73
    After
    0.70
    Finally
    0.70
    rilis
    0.69
     Coim
    0.69
    Then
    0.68
     antik
    0.68
    Later
    0.67
     haba
    0.67
     kemer
    0.67
    Activations Density 0.284%

    No Known Activations