© 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. 13418
    Prev
    Next
    INDEX
    Explanations

    information related to the health benefits of watermelon and vegan diet

    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
    876
    +0.15
    0.5%
    752
    +0.15
    0.5%
    1842
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.15
    0.05
    736
    +0.15
    0.06
    753
    +0.12
    0.01
    Negative Logits
     Krzysz
    -0.81
     kontinu
    -0.66
     kemer
    -0.66
     McLaugh
    -0.65
    InSeconds
    -0.62
     trouw
    -0.61
     Constitucional
    -0.60
    InMillis
    -0.59
    ukunft
    -0.59
    posób
    -0.58
    POSITIVE LOGITS
     ftu
    1.10
     effe
    1.06
     fte
    1.02
     aen
    1.02
     fup
    1.01
     fta
    0.95
     [''
    0.95
     meis
    0.93
     juf
    0.93
     affez
    0.91
    Activations Density 0.327%

    No Known Activations