© 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. 2856
    Prev
    Next
    INDEX
    Explanations

    phrases and questions expressing curiosity about ongoing situations or events

    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
    +0.28
    1.2%
    1637
    +0.09
    0.4%
    156
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.28
    0.03
    468
    +0.09
    0.02
    1372
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.67
     seek
    -0.66
     remove
    -0.64
     eliminate
    -0.62
     add
    -0.59
     assume
    -0.59
     reduce
    -0.58
     choose
    -0.57
     ensure
    -0.56
     acquire
    -0.56
    POSITIVE LOGITS
     Juf
    1.31
     Shakspeare
    1.30
     thut
    1.27
     ftu
    1.25
     fays
    1.24
     Minang
    1.24
     perfon
    1.23
     sovere
    1.22
     fta
    1.21
     malheureux
    1.20
    Activations Density 0.109%

    No Known Activations