© 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 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. 5665
    Prev
    Next
    INDEX
    Explanations

    phrases related to gender roles and societal structures

    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
    964
    +0.09
    0.2%
    623
    +0.08
    0.2%
    1638
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.09
    0.03
    1424
    +0.08
    0.03
    987
    +0.07
    0.03
    Negative Logits
     disagre
    -0.71
     pama
    -0.70
     intersper
    -0.70
     chanced
    -0.69
     apprehen
    -0.69
     lele
    -0.68
     kasa
    -0.67
     umo
    -0.66
     katun
    -0.66
     kani
    -0.63
    POSITIVE LOGITS
     accept
    0.68
     accepting
    0.64
     acceptance
    0.63
    accept
    0.63
     obedient
    0.62
     accepted
    0.62
    acceptance
    0.59
     ACCEPT
    0.58
    accepted
    0.57
     unquestion
    0.56
    Activations Density 0.381%

    No Known Activations