© 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. 239
    Prev
    Next
    INDEX
    Explanations

    words related to research and analysis

    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
    +0.21
    1.0%
    752
    +0.18
    0.8%
    605
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1325
    +0.21
    0.07
    100
    +0.18
    0.06
    569
    +0.11
    0.07
    Negative Logits
    <bos>
    -2.67
     comes
    -0.94
     brought
    -0.94
    for
    -0.92
     put
    -0.90
    of
    -0.88
     goes
    -0.87
     come
    -0.87
    set
    -0.87
     gets
    -0.86
    POSITIVE LOGITS
     Juf
    2.69
     aen
    2.56
     maneu
    2.56
     increa
    2.50
     fta
    2.50
     impra
    2.48
     depic
    2.46
     squa
    2.44
     ftu
    2.38
     wien
    2.38
    Activations Density 0.820%

    No Known Activations