© 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. 3853
    Prev
    Next
    INDEX
    Explanations

    token sequences related to programming functions and concepts

    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
    1553
    +0.08
    0.2%
    1136
    +0.08
    0.2%
    284
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.08
    0.07
    1553
    +0.08
    0.06
    509
    +0.07
    0.06
    Negative Logits
     aen
    -1.26
     meis
    -1.19
     „,
    -1.18
     mef
    -1.15
     gend
    -1.14
     ria
    -1.13
     fei
    -1.12
     franz
    -1.12
     rati
    -1.12
     lele
    -1.11
    POSITIVE LOGITS
     if
    1.32
     when
    1.28
    when
    1.09
     whenever
    1.05
     kapag
    1.05
    if
    1.00
     если
    1.00
     wenn
    0.99
     nếu
    0.97
     dacă
    0.95
    Activations Density 0.454%

    No Known Activations