© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    concepts related to coding practices and functions

    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
    876
    +0.15
    0.4%
    511
    +0.09
    0.3%
    69
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1816
    +0.15
    0.04
    1415
    +0.09
    0.03
    876
    +0.07
    -0.01
    Negative Logits
     kriminal
    -0.80
     Keny
    -0.79
     kompati
    -0.78
     radikal
    -0.76
     Demokrat
    -0.74
     kosme
    -0.74
     akut
    -0.73
     protokol
    -0.73
     panik
    -0.73
     Strukt
    -0.73
    POSITIVE LOGITS
    easier
    0.72
     readability
    0.71
     easier
    0.69
    easily
    0.64
     snad
    0.62
     Easier
    0.61
     traceability
    0.61
     easy
    0.60
     easily
    0.60
     debugging
    0.57
    Activations Density 0.349%

    No Known Activations