© 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. 2038
    Prev
    Next
    INDEX
    Explanations

    dialogue patterns including greetings, introductions, and locations

    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
    599
    +0.08
    0.2%
    674
    +0.08
    0.2%
    2015
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1858
    +0.08
    0.03
    1093
    +0.08
    0.05
    946
    +0.08
    0.04
    Negative Logits
    birthDate
    -0.52
    sergio
    -0.50
     prouve
    -0.50
    Jeudi
    -0.50
     companyId
    -0.49
    Bisous
    -0.49
     heapq
    -0.49
    Lma
    -0.49
    Transcrip
    -0.48
     resultList
    -0.47
    POSITIVE LOGITS
    <bos>
    1.08
    REET
    0.70
     Greetings
    0.65
    itanie
    0.64
     demografica
    0.64
     greetings
    0.63
    parsedMessage
    0.61
     meras
    0.61
     venez
    0.59
    Greetings
    0.58
    Activations Density 0.513%

    No Known Activations