© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3774
    Prev
    Next
    INDEX
    Explanations

    gerunds and present participles

    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
    0.7%
    1691
    +0.12
    0.5%
    1142
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1142
    +0.17
    0.05
    1272
    +0.12
    0.05
    1691
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.30
    Vegeu
    -0.68
    Vlastnosti
    -0.62
    organize
    -0.58
    Particip
    -0.57
     migrate
    -0.55
    IActionResult
    -0.54
    Δείτε
    -0.53
     meet
    -0.52
    Εκ
    -0.52
    POSITIVE LOGITS
     paradiso
    1.17
     thut
    1.13
     unwarran
    1.13
     riviera
    1.11
     ftu
    1.11
     dott
    1.10
     shewn
    1.09
     fta
    1.08
     maroc
    1.08
     😭😭
    1.07
    Activations Density 0.383%

    No Known Activations