© 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. 13353
    Prev
    Next
    INDEX
    Explanations

    mentions of gender, particularly focusing on males and their descriptions

    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
    554
    +0.13
    0.4%
    390
    +0.12
    0.4%
    168
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1516
    +0.13
    0.03
    554
    +0.12
    0.03
    765
    +0.12
    0.03
    Negative Logits
    PhysRevLett
    -0.49
     lanka
    -0.49
     karna
    -0.48
    ntos
    -0.47
    ConverterFactory
    -0.47
     kuli
    -0.47
    resizingMask
    -0.46
    іга
    -0.46
     kuf
    -0.45
     adipis
    -0.45
    POSITIVE LOGITS
     male
    1.18
    Male
    1.09
     Male
    1.08
    male
    1.03
     MALE
    1.01
     males
    0.97
    Males
    0.92
     Males
    0.89
     témoignage
    0.87
     actionTypes
    0.84
    Activations Density 0.052%

    No Known Activations