© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 222
    Prev
    Next
    INDEX
    Explanations

    references to the term "den."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.17
    1.0%
    1323
    +0.14
    0.8%
    228
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    228
    +0.17
    0.03
    1103
    +0.14
    0.03
    1491
    +0.14
    0.03
    Negative Logits
    <bos>
    -2.66
    ‏‏
    -0.60
    <?
    -0.57
     prepare
    -0.54
    asset
    -0.52
     mobilize
    -0.52
     manage
    -0.52
    ittoria
    -0.52
    
    -0.51
     coordinate
    -0.50
    POSITIVE LOGITS
     Den
    1.32
    Den
    1.23
     DEN
    1.22
     Minang
    1.13
     ftre
    1.10
     thut
    1.10
     den
    1.09
     unden
    1.08
     keramik
    1.08
     Juf
    1.07
    Activations Density 0.050%

    No Known Activations