© 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. 13257
    Prev
    Next
    INDEX
    Explanations

    chemical and medical terms related to specific conditions from patient records

    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
    +0.20
    0.6%
    1150
    +0.10
    0.3%
    2034
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1672
    +0.20
    0.03
    1640
    +0.10
    0.02
    279
    +0.09
    0.03
    Negative Logits
     shenan
    -0.69
    telah
    -0.66
     laug
    -0.62
    Să
    -0.62
    ējās
    -0.60
    outdir
    -0.59
     scound
    -0.58
    Și
    -0.58
     Junto
    -0.58
     fuckin
    -0.58
    POSITIVE LOGITS
     lele
    1.18
     kasa
    1.03
     antik
    1.02
     hina
    1.00
     elek
    0.99
     kac
    0.98
     buk
    0.98
     fré
    0.96
     kupa
    0.95
     kram
    0.95
    Activations Density 0.108%

    No Known Activations