© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4092
    Prev
    Next
    INDEX
    Explanations

    terms related to gender equality and gender issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1870
    +0.15
    0.5%
    1077
    +0.13
    0.5%
    765
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1077
    +0.15
    0.02
    765
    +0.13
    0.02
    1044
    +0.13
    0.02
    Negative Logits
    XtraGrid
    -0.53
    AccessFile
    -0.50
    tiembre
    -0.50
    DIPSETTING
    -0.49
    grima
    -0.47
    MouseAdapter
    -0.47
    parsedMessage
    -0.46
    HasColumnName
    -0.45
    appartamento
    -0.44
    ndham
    -0.43
    POSITIVE LOGITS
     gender
    1.24
     Gender
    1.17
    Gender
    1.09
    gender
    1.06
     genders
    0.81
    GENDER
    0.81
    mainwindow
    0.70
     gend
    0.66
     ecclesias
    0.63
     pymysql
    0.63
    Activations Density 0.041%

    No Known Activations