© 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. 6874
    Prev
    Next
    INDEX
    Explanations

    phrases related to age and time

    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
    2000
    +0.09
    0.3%
    674
    +0.09
    0.3%
    1013
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1812
    +0.09
    0.03
    816
    +0.09
    0.03
    1675
    +0.09
    0.03
    Negative Logits
     emphat
    -0.93
     accla
    -0.86
     viciss
    -0.82
     pamph
    -0.81
     Jä
    -0.80
     disgra
    -0.78
    Rgds
    -0.77
     Kün
    -0.77
     apprehen
    -0.77
     benevol
    -0.76
    POSITIVE LOGITS
     too
    0.77
    <bos>
    0.73
     Too
    0.66
    too
    0.64
     to
    0.62
     TOO
    0.61
    Too
    0.59
    InjectAttribute
    0.57
     for
    0.57
    setDo
    0.56
    Activations Density 0.146%

    No Known Activations