© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14763
    Prev
    Next
    INDEX
    Explanations

    phrases indicating funding, projects, and initiatives related to energy and infrastructure

    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
    528
    +0.12
    0.4%
    513
    +0.12
    0.4%
    776
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    528
    +0.12
    0.06
    795
    +0.12
    0.05
    513
    +0.12
    0.05
    Negative Logits
     ananas
    -1.24
     lele
    -1.20
     kram
    -1.15
     makro
    -1.12
     marte
    -1.11
     damen
    -1.11
     meis
    -1.10
     tomat
    -1.10
     karton
    -1.08
     kamb
    -1.07
    POSITIVE LOGITS
     which
    0.89
    which
    0.79
     Which
    0.79
     vainly
    0.74
    Which
    0.74
     consists
    0.71
     includes
    0.69
     comprises
    0.65
     incidentally
    0.65
     has
    0.64
    Activations Density 0.148%

    No Known Activations