© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 1011
    Prev
    Next
    INDEX
    Explanations

    mentions of the male gender

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.09
    0.3%
    1472
    +0.08
    0.3%
    168
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    719
    +0.09
    0.03
    1767
    +0.08
    0.03
    1992
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.56
    //////////
    -0.55
     finalize
    -0.54
    //---
    -0.54
    ///////////////
    -0.54
    ൊ
    -0.50
    public
    -0.49
    			
    -0.49
     rehabilitate
    -0.48
     transact
    -0.48
    POSITIVE LOGITS
     male
    2.08
     Male
    1.97
    Male
    1.89
    male
    1.75
     males
    1.73
     MALE
    1.63
     Males
    1.46
    MALE
    1.37
     mâle
    1.35
    Males
    1.31
    Activations Density 0.082%

    No Known Activations