© 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. 7273
    Prev
    Next
    INDEX
    Explanations

    phrases related to rest, relaxation, or recovery

    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
    1677
    +0.16
    0.6%
    559
    +0.13
    0.5%
    1557
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1677
    +0.16
    0.02
    1557
    +0.13
    0.02
    559
    +0.12
    0.02
    Negative Logits
     pylab
    -0.57
     Fg
    -0.47
     épar
    -0.47
     Hv
    -0.47
     Sarm
    -0.47
     hexadecimal
    -0.46
     skimage
    -0.46
     Consig
    -0.46
     %\
    -0.45
     Pfal
    -0.45
    POSITIVE LOGITS
     rest
    1.12
    Rest
    1.06
    rest
    1.06
     resting
    1.01
     Rest
    1.01
     REST
    0.95
    REST
    0.94
     rested
    0.91
     rests
    0.91
    resting
    0.83
    Activations Density 0.056%

    No Known Activations