© 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. 7298
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions, particularly schools

    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
    687
    +0.14
    0.5%
    1870
    +0.11
    0.4%
    1331
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.14
    0.05
    687
    +0.11
    0.04
    1336
    +0.11
    0.04
    Negative Logits
     intersper
    -0.85
     overcrow
    -0.84
     scrat
    -0.81
     peppa
    -0.78
     disreg
    -0.77
     lapin
    -0.73
     increa
    -0.72
     yves
    -0.72
     nicolas
    -0.71
     kraken
    -0.71
    POSITIVE LOGITS
     school
    1.39
    school
    1.36
    School
    1.31
     School
    1.31
     schools
    1.25
     Schools
    1.17
     SCHOOL
    1.15
    SCHOOL
    1.11
    Schools
    1.11
    chool
    1.09
    Activations Density 0.100%

    No Known Activations