© 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. 12236
    Prev
    Next
    INDEX
    Explanations

    medical terms related to the gastrointestinal system

    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
    198
    +0.16
    0.5%
    1553
    +0.11
    0.3%
    876
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.16
    0.05
    1553
    +0.11
    0.05
    41
    +0.11
    0.04
    Negative Logits
     дописавши
    -0.54
     Whigs
    -0.46
    SqlClient
    -0.46
    TestTools
    -0.45
    mybatisplus
    -0.44
    GOTREF
    -0.42
    <bos>
    -0.41
    signol
    -0.41
     Wakil
    -0.40
    gcf
    -0.40
    POSITIVE LOGITS
     swarovski
    0.73
     ecru
    0.66
     flyknit
    0.65
     ufe
    0.64
     poft
    0.63
     fluo
    0.63
     tricot
    0.63
     ftu
    0.63
     perfon
    0.62
     fendi
    0.62
    Activations Density 0.310%

    No Known Activations