© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2185
    Prev
    Next
    INDEX
    Explanations

    words related to specialization or expertise in a specific field

    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
    370
    +0.14
    0.5%
    866
    +0.13
    0.5%
    1870
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.14
    0.02
    168
    +0.13
    0.02
    866
    +0.13
    0.01
    Negative Logits
     reger
    -0.66
     Vorm
    -0.65
     Ueb
    -0.65
     gesta
    -0.64
     frans
    -0.62
     akus
    -0.61
     gie
    -0.61
     Arbe
    -0.61
     armen
    -0.60
     Gouver
    -0.59
    POSITIVE LOGITS
     specialization
    1.14
     specialize
    1.10
     specializing
    1.07
     specialist
    1.06
     specialty
    1.06
     specialized
    1.06
     specialise
    1.01
     specializes
    1.00
     specialising
    1.00
    specialized
    0.99
    Activations Density 0.054%

    No Known Activations