© 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. 11096
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive pronouns denoting male entities

    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
    50
    +0.12
    0.4%
    1166
    +0.10
    0.3%
    381
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.12
    0.06
    521
    +0.10
    0.07
    1510
    +0.08
    0.07
    Negative Logits
     depic
    -1.94
     accla
    -1.90
     maneu
    -1.88
     shenan
    -1.83
     intersper
    -1.78
     volunte
    -1.77
     encomp
    -1.77
     snoopy
    -1.77
     scrat
    -1.74
     reluct
    -1.74
    POSITIVE LOGITS
     he
    0.88
    He
    0.87
    His
    0.85
     He
    0.84
     his
    0.84
    his
    0.82
     His
    0.79
    he
    0.77
    she
    0.77
    Jäh
    0.75
    Activations Density 0.712%

    No Known Activations