© 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. 11353
    Prev
    Next
    INDEX
    Explanations

    historical or factual information from various fields, including sports, genetics, and family history

    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
    674
    +0.38
    1.5%
    1967
    +0.27
    1.1%
    609
    +0.21
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.38
    0.05
    1967
    +0.27
    0.04
    227
    +0.21
    0.06
    Negative Logits
     tyn
    -0.58
     kras
    -0.54
     saad
    -0.51
     Khart
    -0.50
     betweenstory
    -0.49
     Momb
    -0.49
     Ferdin
    -0.48
     Spani
    -0.48
    Literat
    -0.48
     Koper
    -0.48
    POSITIVE LOGITS
    ⓧ
    0.68
    <bos>
    0.64
    /***
    0.61
     Messieurs
    0.57
     paillettes
    0.54
     soumettre
    0.53
     mourut
    0.51
     irmãos
    0.48
     remercier
    0.46
     hombros
    0.45
    Activations Density 0.592%

    No Known Activations