© 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. 6708
    Prev
    Next
    INDEX
    Explanations

    discussions related to controversies or opinions

    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
    674
    +0.14
    0.4%
    446
    +0.08
    0.2%
    1009
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.06
    155
    +0.08
    0.05
    2044
    +0.07
    0.07
    Negative Logits
     secon
    -1.95
     inev
    -1.90
     fte
    -1.89
     aen
    -1.89
     mef
    -1.85
     accla
    -1.83
     increa
    -1.82
     maneu
    -1.82
     squa
    -1.81
     effe
    -1.81
    POSITIVE LOGITS
     Walkover
    0.75
     only
    0.73
     anyway
    0.72
     without
    0.71
     sagde
    0.70
    Incluso
    0.69
     because
    0.67
     during
    0.67
     alone
    0.67
     directly
    0.66
    Activations Density 0.721%

    No Known Activations