© 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. 6614
    Prev
    Next
    INDEX
    Explanations

    terms related to brewing beer, specifically the process of making beer

    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
    +0.20
    0.6%
    1013
    +0.14
    0.5%
    736
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.20
    0.07
    1551
    +0.14
    0.04
    753
    +0.14
    0.01
    Negative Logits
     Jurist
    -0.85
     Rektor
    -0.80
     monaster
    -0.76
     ecclesias
    -0.75
     menyen
    -0.71
     cristi
    -0.71
     Senat
    -0.70
     Presidencia
    -0.69
     Kriminal
    -0.69
     Schalke
    -0.68
    POSITIVE LOGITS
     ftu
    1.52
     thut
    1.38
     tranf
    1.34
     poff
    1.33
     fta
    1.32
     perfon
    1.30
     feen
    1.29
     fup
    1.28
     foon
    1.23
     ftre
    1.23
    Activations Density 0.386%

    No Known Activations