© 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. 1741
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptors related to complexity and quality

    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
    +0.26
    1.1%
    1385
    +0.20
    0.8%
    198
    +0.19
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.26
    0.11
    198
    +0.20
    0.10
    605
    +0.19
    0.04
    Negative Logits
    <bos>
    -2.26
     négociations
    -0.88
     prochaines
    -0.88
     procédures
    -0.86
     modalités
    -0.86
     épreuves
    -0.85
     débats
    -0.77
     vœux
    -0.74
     pouvoirs
    -0.74
     écrans
    -0.74
    POSITIVE LOGITS
     riva
    1.31
     hcm
    1.30
     jaya
    1.28
     bandung
    1.28
     lele
    1.24
     quoc
    1.21
     aen
    1.11
     Minang
    1.11
     vinci
    1.08
     vecchia
    1.07
    Activations Density 0.503%

    No Known Activations