© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13091
    Prev
    Next
    INDEX
    Explanations

    verbal phrases related to teaching or 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
    1372
    +0.09
    0.3%
    9
    +0.08
    0.2%
    1166
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1372
    +0.09
    0.04
    470
    +0.08
    0.04
    1512
    +0.08
    0.03
    Negative Logits
     depic
    -1.35
     unden
    -1.34
     reluct
    -1.30
     inev
    -1.28
     guarante
    -1.28
     encomp
    -1.27
     accla
    -1.27
     shenan
    -1.23
     unve
    -1.22
     wherea
    -1.21
    POSITIVE LOGITS
     learn
    0.83
    learn
    0.75
     learned
    0.74
     Learn
    0.73
    Learn
    0.72
     how
    0.68
     lessons
    0.68
     learnt
    0.67
     skills
    0.67
     learning
    0.64
    Activations Density 0.238%

    No Known Activations