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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13721
    Prev
    Next
    INDEX
    Explanations

    gender-related words and phrases, including concepts of male dominance, female submission, and gender roles

    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
    1842
    +0.12
    0.3%
    964
    +0.10
    0.3%
    198
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1948
    +0.12
    0.05
    1608
    +0.10
    0.02
    1366
    +0.09
    0.03
    Negative Logits
     makro
    -0.78
     kaos
    -0.73
     aton
    -0.69
     kram
    -0.67
     lele
    -0.66
     fortn
    -0.66
     teras
    -0.65
     saba
    -0.65
     usta
    -0.65
     saar
    -0.65
    POSITIVE LOGITS
     husbands
    0.56
     women
    0.54
    توضیحات
    0.52
     husband
    0.52
     wives
    0.51
     Mulher
    0.50
     homemaker
    0.50
     herself
    0.50
    obiety
    0.49
    kaufs
    0.48
    Activations Density 0.413%

    No Known Activations