© 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. 12729
    Prev
    Next
    INDEX
    Explanations

    instances of people being aware of certain situations or information

    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
    1265
    +0.14
    0.5%
    1379
    +0.14
    0.5%
    1573
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1379
    +0.14
    0.03
    1573
    +0.14
    0.03
    1265
    +0.14
    0.03
    Negative Logits
    ₂)
    -0.50
     erd
    -0.50
     kram
    -0.49
     eme
    -0.49
    itag
    -0.49
    ₂,
    -0.48
     Strukt
    -0.48
     Dosen
    -0.47
     klu
    -0.47
    thun
    -0.47
    POSITIVE LOGITS
     aware
    1.17
     awareness
    1.07
     Awareness
    1.02
     Aware
    1.02
    aware
    1.01
    awareness
    0.98
    Awareness
    0.97
    Aware
    0.86
     unaware
    0.73
     consciente
    0.61
    Activations Density 0.057%

    No Known Activations