© 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. 7364
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions

    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
    453
    +0.12
    0.3%
    876
    +0.12
    0.3%
    1842
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.12
    0.02
    11
    +0.12
    0.02
    453
    +0.12
    0.02
    Negative Logits
     impractica
    -0.64
     ujedno
    -0.63
     renfer
    -0.62
    Sklici
    -0.61
     empêche
    -0.60
     semblait
    -0.58
     unlaw
    -0.57
     pamph
    -0.56
     aislada
    -0.56
    Avantages
    -0.55
    POSITIVE LOGITS
     aspetta
    0.91
     trovo
    0.90
     sento
    0.81
     chèvre
    0.78
     broderie
    0.74
     desideri
    0.73
     migli
    0.72
     lancia
    0.72
     trasforma
    0.71
     nicolas
    0.71
    Activations Density 0.078%

    No Known Activations