© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2519
    Prev
    Next
    INDEX
    Explanations

    information related to education, specifically focusing on homeschooling vs. traditional schooling and online 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
    674
    +0.10
    0.3%
    1823
    +0.07
    0.2%
    1252
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.10
    0.04
    1415
    +0.07
    0.02
    1475
    +0.07
    0.02
    Negative Logits
     reluct
    -1.92
     disagre
    -1.91
     Juf
    -1.87
     encomp
    -1.86
     volunte
    -1.85
     philanth
    -1.81
     impra
    -1.80
     depic
    -1.78
     shenan
    -1.77
     maneu
    -1.77
    POSITIVE LOGITS
    <bos>
    1.33
    AndEndTag
    1.01
     bağlantılar
    0.89
    setVerticalGroup
    0.88
    Geplaatst
    0.86
    AddTagHelper
    0.83
     gainera
    0.80
     rhestr
    0.79
     saites
    0.77
    findpost
    0.76
    Activations Density 0.451%

    No Known Activations