© 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. 12030
    Prev
    Next
    INDEX
    Explanations

    personal opinions and expressions of strong emotions

    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
    478
    +0.14
    0.5%
    658
    +0.13
    0.5%
    645
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.14
    0.05
    645
    +0.13
    0.04
    805
    +0.13
    0.04
    Negative Logits
     saha
    -0.78
     seksi
    -0.77
     jaya
    -0.76
     silikon
    -0.74
    capulco
    -0.73
     susun
    -0.72
     kafe
    -0.72
     bayan
    -0.71
     thuy
    -0.70
     hina
    -0.70
    POSITIVE LOGITS
     Estaba
    0.80
    Dés
    0.79
     intersper
    0.78
     am
    0.76
    Dziękuję
    0.75
    posób
    0.74
    voici
    0.71
    Díky
    0.71
    pozdrawiam
    0.70
     Estou
    0.69
    Activations Density 0.114%

    No Known Activations