© 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. 11963
    Prev
    Next
    INDEX
    Explanations

    conversations and interactions between multiple speakers

    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
    2019
    +0.17
    0.5%
    1741
    +0.17
    0.5%
    381
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    454
    +0.17
    0.02
    1574
    +0.17
    0.02
    1959
    +0.14
    0.02
    Negative Logits
     dises
    -1.59
     territo
    -1.47
     magis
    -1.40
     lemp
    -1.39
     imbal
    -1.29
     alkoh
    -1.27
     Minang
    -1.26
     kram
    -1.26
     saar
    -1.23
     abnorm
    -1.20
    POSITIVE LOGITS
     Yes
    0.87
     Yeah
    0.85
     So
    0.85
     That
    0.83
     Well
    0.80
     And
    0.80
     Then
    0.79
     It
    0.78
     But
    0.78
     There
    0.78
    Activations Density 0.036%

    No Known Activations