© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2610
    Prev
    Next
    INDEX
    Explanations

    subjects or pronouns that refer to individuals

    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
    +0.34
    1.8%
    920
    +0.15
    0.8%
    1178
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    920
    +0.34
    0.08
    1178
    +0.15
    0.06
    812
    +0.14
    0.05
    Negative Logits
    <bos>
    -2.39
     solidar
    -0.75
    औ
    -0.62
     facilite
    -0.62
    col
    -0.61
     gela
    -0.60
     col
    -0.60
     cu
    -0.59
     hiper
    -0.57
    CreateIndex
    -0.57
    POSITIVE LOGITS
     unlaw
    1.71
     impractica
    1.62
     unwarran
    1.61
     disagre
    1.58
     wherea
    1.55
     liberality
    1.52
     ingrat
    1.51
     accla
    1.51
     sovere
    1.51
     increa
    1.48
    Activations Density 0.167%

    No Known Activations