© 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. 4613
    Prev
    Next
    INDEX
    Explanations

    contractions of "is not" with high activation values

    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
    478
    +0.15
    0.5%
    674
    +0.12
    0.4%
    1323
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1313
    +0.15
    0.05
    1337
    +0.12
    0.05
    1604
    +0.12
    0.04
    Negative Logits
     Maude
    -0.56
     Morton
    -0.55
    Dermott
    -0.51
     Justo
    -0.50
     Schulze
    -0.49
     Leal
    -0.49
    Grath
    -0.48
     Felicia
    -0.48
    área
    -0.48
    bouncycastle
    -0.48
    POSITIVE LOGITS
     fatis
    1.07
     igno
    1.01
     effe
    0.98
     difp
    0.96
     paff
    0.94
     ordina
    0.91
     credere
    0.91
     obfer
    0.91
     abbra
    0.90
     sappi
    0.90
    Activations Density 0.100%

    No Known Activations