© 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. 7080
    Prev
    Next
    INDEX
    Explanations

    keywords related to setting up initiatives or projects, such as funds, accounts, appointments, or programs

    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
    1757
    +0.17
    0.6%
    82
    +0.11
    0.4%
    2011
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1757
    +0.17
    0.03
    82
    +0.11
    0.02
    2011
    +0.10
    0.02
    Negative Logits
     accla
    -0.69
     coö
    -0.68
     igno
    -0.67
     exorbit
    -0.66
     Febru
    -0.66
     pessi
    -0.65
     acce
    -0.63
     embra
    -0.63
     byz
    -0.61
     fath
    -0.60
    POSITIVE LOGITS
     setup
    1.02
    setup
    0.97
     setups
    0.97
     Setup
    0.95
    Setup
    0.86
    SETUP
    0.85
     SETUP
    0.84
     setUp
    0.77
    setUp
    0.72
     up
    0.65
    Activations Density 0.073%

    No Known Activations