© 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. 14754
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions represented in text format

    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
    +0.15
    0.5%
    204
    +0.14
    0.5%
    874
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.15
    0.01
    874
    +0.14
    0.01
    924
    +0.13
    0.01
    Negative Logits
     Punj
    -0.64
     prek
    -0.60
     lebte
    -0.58
     schloss
    -0.57
     slika
    -0.56
     schlug
    -0.55
     kral
    -0.52
     rief
    -0.52
     suchte
    -0.52
     legte
    -0.52
    POSITIVE LOGITS
     quæ
    0.99
     jacques
    0.98
     potest
    0.97
     habet
    0.96
    
    0.94
     vinci
    0.91
     ejus
    0.90
     tanong
    0.88
     Messieurs
    0.87
     grati
    0.87
    Activations Density 0.042%

    No Known Activations