© 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. 4637
    Prev
    Next
    INDEX
    Explanations

    words related to technology, specifically artificial intelligence and computer interactions

    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
    +0.10
    0.3%
    1842
    +0.09
    0.2%
    509
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1409
    +0.10
    0.02
    106
    +0.09
    0.04
    2045
    +0.08
    0.04
    Negative Logits
     impra
    -1.08
     shenan
    -1.06
     reluct
    -1.03
     maneu
    -1.00
     depic
    -1.00
     excru
    -0.97
     uninten
    -0.94
     Souha
    -0.93
     Juf
    -0.92
     accla
    -0.92
    POSITIVE LOGITS
     plus
    0.56
     deadlines
    0.55
     complex
    0.55
     constantly
    0.54
     demanding
    0.54
     stressful
    0.53
     unfamiliar
    0.53
     dealing
    0.52
    uxxxx
    0.51
     demands
    0.51
    Activations Density 0.617%

    No Known Activations