© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6041
    Prev
    Next
    INDEX
    Explanations

    numerical sequences or patterns

    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
    1343
    +0.09
    0.2%
    1897
    +0.07
    0.2%
    1686
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.03
    1274
    +0.07
    0.02
    730
    +0.07
    0.02
    Negative Logits
    AndEndTag
    -0.59
     елның
    -0.56
    piram
    -0.52
     kasarigan
    -0.51
    IUrlHelper
    -0.49
     insuffisamment
    -0.48
    новништво
    -0.48
    Geplaatst
    -0.47
     noten
    -0.45
    AsUp
    -0.45
    POSITIVE LOGITS
     disreg
    0.83
     indestru
    0.81
    Histology
    0.79
     kontinu
    0.78
    Transcrip
    0.75
     inconce
    0.72
     perfet
    0.70
     embodi
    0.70
     viciss
    0.70
     accla
    0.68
    Activations Density 0.096%

    No Known Activations