© 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. 12399
    Prev
    Next
    INDEX
    Explanations

    references to museums and related activities

    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
    144
    +0.18
    0.7%
    421
    +0.13
    0.5%
    1757
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.18
    0.03
    789
    +0.13
    0.03
    537
    +0.13
    0.03
    Negative Logits
     intersper
    -1.35
     encomp
    -1.18
     purcha
    -1.14
     depic
    -1.13
     accla
    -1.11
     scrat
    -1.09
     impra
    -1.09
     reluct
    -1.07
     increa
    -1.07
     inev
    -1.07
    POSITIVE LOGITS
     museum
    1.53
     Museum
    1.48
    Museum
    1.36
     museums
    1.36
    museum
    1.32
     Museums
    1.14
     MUSEUM
    1.08
    Museums
    0.93
     museo
    0.91
    Museo
    0.89
    Activations Density 0.073%

    No Known Activations