© 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. 11858
    Prev
    Next
    INDEX
    Explanations

    references to international relations and military activities involving the United States

    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
    1978
    +0.09
    0.3%
    604
    +0.09
    0.3%
    1510
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1252
    +0.09
    0.06
    512
    +0.09
    0.05
    1510
    +0.09
    0.04
    Negative Logits
     thut
    -0.84
     tranf
    -0.82
     dirait
    -0.82
     perfon
    -0.82
     gaily
    -0.81
     ftu
    -0.80
     intersper
    -0.79
     reft
    -0.78
     lele
    -0.78
     fep
    -0.77
    POSITIVE LOGITS
    US
    0.59
     US
    0.57
    ngiliz
    0.56
    USA
    0.50
    řevě
    0.47
     USA
    0.47
    lcccccc
    0.46
    +"/"+
    0.46
    zyden
    0.45
    strokeStyle
    0.45
    Activations Density 0.194%

    No Known Activations