© 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. 3851
    Prev
    Next
    INDEX
    Explanations

    dates and years in the 1980s and 1990s

    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
    1965
    +0.09
    0.3%
    577
    +0.09
    0.3%
    766
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.09
    0.06
    1313
    +0.09
    0.05
    766
    +0.08
    0.06
    Negative Logits
     tille
    -0.70
     ananas
    -0.70
     ciment
    -0.66
     alfabe
    -0.65
     vasi
    -0.64
     spion
    -0.64
     aquare
    -0.63
     sò
    -0.61
     pò
    -0.60
     basili
    -0.59
    POSITIVE LOGITS
     apprehen
    0.81
     disagre
    0.78
     vainly
    0.77
     abounds
    0.76
     blest
    0.72
     quitted
    0.72
     nobly
    0.71
     unwarran
    0.71
     tolerably
    0.70
     upvoted
    0.67
    Activations Density 0.517%

    No Known Activations