© 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. 4578
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses in the text

    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
    +0.31
    1.4%
    2019
    +0.10
    0.5%
    950
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    950
    +0.31
    0.07
    331
    +0.10
    0.06
    667
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.29
    ⓧ
    -1.01
    /**
    -0.74
     himo
    -0.74
    
    -0.74
     AssemblyCompany
    -0.66
    Personendaten
    -0.66
     springfox
    -0.65
     '/':
    -0.63
    rungsseite
    -0.62
    POSITIVE LOGITS
     maneu
    1.36
     affor
    1.31
     inev
    1.26
     ftu
    1.23
     accla
    1.22
     resear
    1.21
     Keny
    1.20
     volunte
    1.19
     depic
    1.17
     fta
    1.16
    Activations Density 0.165%

    No Known Activations