© 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. 4257
    Prev
    Next
    INDEX
    Explanations

    mentions of education and learning

    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
    1614
    +0.11
    0.3%
    194
    +0.07
    0.2%
    1260
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1614
    +0.11
    0.05
    1648
    +0.07
    0.02
    623
    +0.07
    0.04
    Negative Logits
     Jambi
    -0.63
     bawat
    -0.56
    ftagPool
    -0.56
    🕗
    -0.54
     Palembang
    -0.54
     Karang
    -0.53
     Banten
    -0.53
     tanong
    -0.53
     Kampung
    -0.53
     sumamente
    -0.52
    POSITIVE LOGITS
     Ename
    0.65
     Blinds
    0.60
     divertimento
    0.59
     AWG
    0.56
     palio
    0.55
     swarovski
    0.55
     fumo
    0.55
     imposs
    0.54
     embodi
    0.53
     Stretcher
    0.53
    Activations Density 0.309%

    No Known Activations