© 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. 4514
    Prev
    Next
    INDEX
    Explanations

    references to uncertainty or hesitation, particularly in speech

    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
    +0.13
    0.8%
    90
    +0.13
    0.8%
    537
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.13
    0.04
    1451
    +0.13
    0.02
    1363
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.00
    /***
    -0.62
     cooperated
    -0.57
     onBackPressed
    -0.56
     broaden
    -0.55
    
    -0.54
     cooperate
    -0.54
    ⓧ
    -0.51
     prosecute
    -0.51
    Мон
    -0.50
    POSITIVE LOGITS
     Pum
    1.10
     Ruman
    1.04
     DUM
    0.97
     Neum
    0.90
     Krum
    0.90
     plong
    0.89
     Jum
    0.88
     circon
    0.88
    um
    0.87
     Brum
    0.86
    Activations Density 0.158%

    No Known Activations