© 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. 14840
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, such as cities and regions

    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
    1861
    +0.10
    0.3%
    1137
    +0.08
    0.2%
    289
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.10
    0.06
    981
    +0.08
    0.06
    1439
    +0.08
    0.04
    Negative Logits
     nakalista
    -0.74
     lapto
    -0.56
     sicura
    -0.54
     affez
    -0.53
    writeFieldEnd
    -0.52
     EconPapers
    -0.52
    ֗
    -0.51
     AppColors
    -0.51
    ))^{
    -0.51
    ֔
    -0.49
    POSITIVE LOGITS
     depic
    0.90
     disagre
    0.84
     Messieurs
    0.81
     inev
    0.81
     fta
    0.79
     madonna
    0.79
     fuf
    0.79
     ftu
    0.78
     fath
    0.78
     Mlle
    0.77
    Activations Density 0.275%

    No Known Activations