© 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. 1927
    Prev
    Next
    INDEX
    Explanations

    references to investigations and political figures

    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
    1842
    +0.21
    0.6%
    1177
    +0.10
    0.3%
    344
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1571
    +0.21
    0.04
    344
    +0.10
    0.04
    1001
    +0.10
    0.05
    Negative Logits
     swarovski
    -1.03
     ecru
    -0.93
     hairc
    -0.88
     bonbons
    -0.86
     tupperware
    -0.84
     nutella
    -0.82
     amigurumi
    -0.81
     oreo
    -0.80
     cushi
    -0.80
     embodi
    -0.79
    POSITIVE LOGITS
     biograf
    0.62
     praktik
    0.62
     Sekret
    0.58
     Dä
    0.55
     kram
    0.55
     Itali
    0.55
     häm
    0.55
     sexu
    0.55
     kosme
    0.55
    ukone
    0.55
    Activations Density 0.719%

    No Known Activations