© 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. 7336
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms related to category theory and control theory

    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
    +0.27
    0.9%
    2015
    +0.20
    0.7%
    1553
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.27
    -0.00
    1553
    +0.20
    0.05
    51
    +0.16
    0.02
    Negative Logits
     Premios
    -0.80
     Fuerzas
    -0.80
     Juventud
    -0.79
     Komis
    -0.75
     republi
    -0.71
     Naciones
    -0.70
    BASELINE
    -0.69
     Gouver
    -0.67
     Nación
    -0.66
    DoubleQuotes
    -0.66
    POSITIVE LOGITS
     jacques
    1.69
     levis
    1.67
     napoli
    1.63
     squa
    1.60
     waer
    1.56
     lyon
    1.54
     peppa
    1.52
     wien
    1.50
     laurent
    1.48
     effe
    1.47
    Activations Density 0.293%

    No Known Activations