© 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. 6459
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Gary" preceded by or followed by a certain context or action

    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
    1092
    +0.15
    0.6%
    1177
    +0.12
    0.5%
    1763
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1092
    +0.15
    0.02
    981
    +0.12
    0.02
    1097
    +0.11
    0.02
    Negative Logits
     unspeak
    -0.77
     pageNum
    -0.61
     precipice
    -0.57
     indescri
    -0.57
     bulkhead
    -0.53
     Abhishek
    -0.52
     sanctity
    -0.51
     sophistic
    -0.50
     totalCount
    -0.50
     Dietz
    -0.50
    POSITIVE LOGITS
     Gary
    1.30
    Gary
    1.24
     Traité
    1.04
    GARY
    1.03
    gary
    0.94
     gesta
    0.93
     Mémoires
    0.89
     kosme
    0.89
     aquare
    0.84
     alkoh
    0.84
    Activations Density 0.118%

    No Known Activations