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

    Neuronpedia

    Jacobian LensNEW
    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. 11262
    Prev
    Next
    INDEX
    Explanations

    succinct summaries or bullet points in a document

    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
    1044
    +0.13
    0.4%
    1839
    +0.12
    0.4%
    849
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1044
    +0.13
    0.03
    849
    +0.12
    0.03
    461
    +0.10
    0.01
    Negative Logits
     discogs
    -0.81
     Rodrig
    -0.81
     bordeaux
    -0.77
     blackpink
    -0.77
     michelin
    -0.76
     hasbro
    -0.76
    🕗
    -0.74
     geforce
    -0.73
     prada
    -0.73
     nutella
    -0.73
    POSITIVE LOGITS
     summary
    1.29
     Summary
    1.17
    Summary
    1.11
    summary
    1.10
     summaries
    1.09
     summarize
    1.07
     summarizing
    1.02
     summarizes
    1.00
    SUMMARY
    0.99
     summarized
    0.97
    Activations Density 0.119%

    No Known Activations