© 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. 13219
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological developments and industry analysis

    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
    138
    +0.10
    0.3%
    803
    +0.09
    0.3%
    870
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    870
    +0.10
    0.04
    1038
    +0.09
    0.03
    803
    +0.08
    0.04
    Negative Logits
     disreg
    -1.09
     disagre
    -1.04
     affor
    -0.99
     inconce
    -0.98
     cytoplas
    -0.97
     strick
    -0.94
     unspeak
    -0.91
     impra
    -0.91
     encomp
    -0.90
     inev
    -0.90
    POSITIVE LOGITS
    new
    1.04
     new
    0.96
     nuevos
    0.81
     nueva
    0.75
     addition
    0.75
     additions
    0.74
     nuevas
    0.72
     newcomers
    0.71
    NEW
    0.71
    新的
    0.71
    Activations Density 0.554%

    No Known Activations