© 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. 12616
    Prev
    Next
    INDEX
    Explanations

    mentions of technology-related terms and programming concepts such as Bluetooth, installations, and protocols

    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
    1048
    +0.09
    0.3%
    872
    +0.08
    0.2%
    1643
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.09
    0.07
    1257
    +0.08
    0.05
    468
    +0.07
    0.05
    Negative Logits
     alkoh
    -0.96
     kollek
    -0.91
     kön
    -0.90
     kosme
    -0.87
     solidar
    -0.86
     embra
    -0.86
     §.
    -0.86
     „,
    -0.85
     Chá
    -0.84
     sii
    -0.84
    POSITIVE LOGITS
     nor
    1.09
     anymore
    0.81
    Diwedd
    0.73
     or
    0.73
     Tampoco
    0.69
     sondern
    0.68
    Cześć
    0.66
    而是
    0.66
     whatsoever
    0.63
    nor
    0.62
    Activations Density 1.159%

    No Known Activations