© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13772
    Prev
    Next
    INDEX
    Explanations

    pronouns, particularly the word "they"

    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
    1034
    +0.11
    0.3%
    381
    +0.10
    0.3%
    814
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1034
    +0.11
    0.07
    1919
    +0.10
    0.07
    1415
    +0.09
    0.04
    Negative Logits
     panama
    -1.04
     jurassic
    -1.03
     squa
    -1.00
     stockholm
    -0.98
     franz
    -0.96
     Comand
    -0.96
     fatis
    -0.95
     vhs
    -0.94
     claudia
    -0.94
     budapest
    -0.94
    POSITIVE LOGITS
    They
    0.81
    they
    0.78
     they
    0.78
     They
    0.74
    THEY
    0.73
    Their
    0.72
     themselves
    0.71
    their
    0.69
     THEY
    0.67
     họ
    0.66
    Activations Density 0.353%

    No Known Activations