© 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. 6644
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Amid" in the text

    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
    897
    +0.13
    0.4%
    1678
    +0.12
    0.4%
    1035
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1035
    +0.13
    0.02
    1678
    +0.12
    0.02
    1351
    +0.11
    0.01
    Negative Logits
     Moderately
    -0.53
     Conclu
    -0.52
     contribue
    -0.52
     Ubic
    -0.48
     Necess
    -0.47
    ToRead
    -0.47
     Morphology
    -0.47
     Throwing
    -0.47
    Ontology
    -0.47
     Rese
    -0.46
    POSITIVE LOGITS
     amid
    0.90
    Amid
    0.83
     amidst
    0.79
     raggiunto
    0.74
     Amid
    0.73
    amid
    0.73
     pensato
    0.65
     fornito
    0.64
     lasciato
    0.64
    estanding
    0.59
    Activations Density 0.065%

    No Known Activations