© 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. 4530
    Prev
    Next
    INDEX
    Explanations

    passages describing sports plays or actions

    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
    906
    +0.18
    0.5%
    1842
    +0.13
    0.4%
    1385
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.18
    0.04
    825
    +0.13
    0.04
    1496
    +0.13
    0.04
    Negative Logits
     Whence
    -0.88
     affez
    -0.84
     unwarran
    -0.77
     tolerably
    -0.72
    SBATCH
    -0.72
     cytoplas
    -0.69
     unlaw
    -0.68
     fortn
    -0.67
     shewn
    -0.66
     coö
    -0.66
    POSITIVE LOGITS
     palet
    0.63
     defekt
    0.63
     utop
    0.61
     kompakt
    0.60
    <bos>
    0.60
     kön
    0.59
     Bakter
    0.58
     buro
    0.57
     makro
    0.57
     kooper
    0.57
    Activations Density 0.210%

    No Known Activations