© 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. 3706
    Prev
    Next
    INDEX
    Explanations

    references to gender, particularly focusing on masculinity and the male experience

    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
    1.1%
    1516
    +0.10
    0.4%
    1950
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1516
    +0.28
    0.05
    1992
    +0.10
    0.05
    122
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.49
    AutoScaleMode
    -0.74
    queryInterface
    -0.73
    /*---
    -0.70
    <!--
    -0.69
     Normdatei
    -0.68
    IVEREF
    -0.67
    Šaltiniai
    -0.67
    AutoScale
    -0.64
    contentLoaded
    -0.64
    POSITIVE LOGITS
     ecru
    1.75
     swarovski
    1.56
     impractica
    1.46
     peppa
    1.45
     nutella
    1.40
     indestru
    1.35
     disreg
    1.33
     unlaw
    1.31
     Minang
    1.31
     jurassic
    1.30
    Activations Density 0.285%

    No Known Activations