© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12519
    Prev
    Next
    INDEX
    Explanations

    JSON formatted data strings

    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
    2019
    +0.22
    0.7%
    453
    +0.18
    0.6%
    876
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.22
    0.03
    876
    +0.18
    0.00
    1871
    +0.15
    0.02
    Negative Logits
     mécanisme
    -0.81
     Handmaid
    -0.77
     levier
    -0.74
     pétrole
    -0.72
     One
    -0.71
     noyau
    -0.70
     The
    -0.70
     thunderbolt
    -0.69
     tournant
    -0.69
     bénéfice
    -0.68
    POSITIVE LOGITS
     dises
    1.70
     canel
    1.64
     pican
    1.64
     erec
    1.62
     magis
    1.61
     doman
    1.57
     nutr
    1.54
     uniti
    1.51
     socie
    1.50
     grati
    1.48
    Activations Density 0.074%

    No Known Activations