© 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. 12658
    Prev
    Next
    INDEX
    Explanations

    statistics and political figures or terms

    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
    1842
    +0.19
    0.5%
    453
    +0.14
    0.4%
    599
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1897
    +0.19
    0.02
    1586
    +0.14
    0.03
    1114
    +0.12
    0.03
    Negative Logits
     encomp
    -1.41
     inev
    -1.36
     reluct
    -1.33
     uninten
    -1.29
     suscep
    -1.28
     accla
    -1.28
     intermitt
    -1.23
     coö
    -1.23
     increa
    -1.22
     unden
    -1.21
    POSITIVE LOGITS
    FlatAppearance
    0.57
     overall
    0.55
    ChatColor
    0.54
    /
    0.52
    About
    0.50
     about
    0.50
     or
    0.49
     oder
    0.49
     About
    0.48
     «
    0.48
    Activations Density 0.314%

    No Known Activations