© 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. 4070
    Prev
    Next
    INDEX
    Explanations

    statements of authority or notable quotes in a political context

    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
    +0.36
    1.8%
    394
    +0.24
    1.2%
    1577
    +0.21
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.36
    0.33
    1129
    +0.24
    0.24
    461
    +0.21
    0.14
    Negative Logits
    <bos>
    -2.06
     intersper
    -1.22
    ⓧ
    -1.17
     quitted
    -1.13
     encomp
    -1.12
     unve
    -1.09
     purcha
    -1.07
    <?
    -1.03
     disambigu
    -1.03
     forbear
    -1.02
    POSITIVE LOGITS
     marea
    0.62
     Teknik
    0.58
     [
    0.57
     cortina
    0.53
     barca
    0.52
     capitan
    0.52
     Muhamma
    0.51
     barcel
    0.51
     grava
    0.50
     fundamenta
    0.50
    Activations Density 10.830%

    No Known Activations