© 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. 6254
    Prev
    Next
    INDEX
    Explanations

    sequences of dates represented in numbers

    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
    1343
    +0.13
    0.5%
    1137
    +0.12
    0.5%
    1065
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1065
    +0.13
    0.06
    609
    +0.12
    0.05
    577
    +0.12
    0.06
    Negative Logits
     poetical
    -0.62
     underta
    -0.60
     psal
    -0.60
     scottish
    -0.59
     pamph
    -0.59
     philo
    -0.57
     ferrari
    -0.57
     epistle
    -0.55
     philips
    -0.54
     Kün
    -0.54
    POSITIVE LOGITS
    awtextra
    0.80
     susun
    0.66
     naer
    0.65
     maksi
    0.64
     karton
    0.64
     quoc
    0.62
     kado
    0.61
     saad
    0.61
     bawat
    0.61
     tanong
    0.60
    Activations Density 0.197%

    No Known Activations