© 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. 11999
    Prev
    Next
    INDEX
    Explanations

    details about events and gatherings involving various people, such as residents, officials, and strangers

    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
    227
    +0.09
    0.3%
    599
    +0.08
    0.2%
    114
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.09
    0.03
    1235
    +0.08
    0.04
    862
    +0.08
    0.03
    Negative Logits
     fédé
    -0.67
     compét
    -0.66
     êtres
    -0.63
     quegli
    -0.61
     ouvriers
    -0.58
     écout
    -0.58
     laajenta
    -0.55
     pères
    -0.55
     fidèles
    -0.54
    Rgds
    -0.54
    POSITIVE LOGITS
     alike
    1.83
    alike
    0.96
     respectively
    0.76
    respectively
    0.71
     drap
    0.70
     plak
    0.67
     stoff
    0.64
     interchangeably
    0.64
     kram
    0.63
     stik
    0.62
    Activations Density 0.354%

    No Known Activations