© 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. 12061
    Prev
    Next
    INDEX
    Explanations

    verbs related to analyzing information and drawing conclusions

    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
    872
    +0.08
    0.2%
    715
    +0.08
    0.2%
    1056
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    368
    +0.08
    0.04
    1786
    +0.08
    0.02
    715
    +0.08
    0.02
    Negative Logits
     reluct
    -0.76
     Timp
    -0.74
     cuban
    -0.73
     squa
    -0.72
     compen
    -0.71
     Sarm
    -0.71
     disgra
    -0.70
     tropic
    -0.70
     ariel
    -0.70
     Lyd
    -0.69
    POSITIVE LOGITS
     conclusion
    1.52
     conclusions
    1.43
     conclude
    1.24
    conclusion
    1.20
     Conclusion
    1.19
     Conclusions
    1.17
    Conclusion
    1.11
    Conclusions
    1.09
     concluded
    1.08
     conclu
    1.06
    Activations Density 0.221%

    No Known Activations