© 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. 6285
    Prev
    Next
    INDEX
    Explanations

    text related to news headlines or articles

    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
    2019
    +0.36
    1.3%
    184
    +0.23
    0.8%
    1535
    +0.22
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.36
    0.04
    946
    +0.23
    0.04
    1535
    +0.22
    0.04
    Negative Logits
     CHLOR
    -0.74
     tupperware
    -0.68
    requently
    -0.68
     duster
    -0.67
     VOOR
    -0.66
    roidery
    -0.65
     BORROW
    -0.63
     HÀ
    -0.62
     POLLUTION
    -0.61
     FURNITURE
    -0.60
    POSITIVE LOGITS
     Quod
    1.01
     Juf
    0.99
     Coim
    0.97
     antik
    0.88
     Augu
    0.87
     Keny
    0.87
     fta
    0.86
     istan
    0.85
     fte
    0.84
     trasparente
    0.83
    Activations Density 0.066%

    No Known Activations