© 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. 5852
    Prev
    Next
    INDEX
    Explanations

    numerical sequences

    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
    479
    +0.14
    0.5%
    544
    +0.14
    0.5%
    1961
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1520
    +0.14
    0.06
    893
    +0.14
    0.05
    1562
    +0.14
    0.06
    Negative Logits
    scalatest
    -0.48
    Elő
    -0.48
     betweenstory
    -0.48
    setupUi
    -0.44
    Gemeinde
    -0.44
    fortawesome
    -0.43
    உ
    -0.43
     сте
    -0.41
     faça
    -0.41
     plant
    -0.41
    POSITIVE LOGITS
     dispen
    0.80
     paillettes
    0.74
     lancia
    0.73
     embra
    0.72
     napoli
    0.71
     🤣🤣
    0.71
     broderie
    0.71
     javier
    0.70
     !...
    0.70
     🙃
    0.70
    Activations Density 0.216%

    No Known Activations