© 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. 11725
    Prev
    Next
    INDEX
    Explanations

    information related to meetings, reports, and documents

    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
    1699
    +0.18
    0.6%
    906
    +0.18
    0.6%
    1403
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1793
    +0.18
    0.06
    924
    +0.18
    0.06
    227
    +0.15
    0.07
    Negative Logits
     자신의
    -0.75
     сми
    -0.73
    들에게
    -0.72
     било
    -0.72
     глазах
    -0.71
     그것
    -0.70
     serious
    -0.70
     democratic
    -0.70
     ہی
    -0.69
     robi
    -0.69
    POSITIVE LOGITS
     vété
    1.76
     hcm
    1.72
     confé
    1.62
     télécharge
    1.62
     Outils
    1.62
     Chapitre
    1.61
     rafra
    1.60
     Gouvernement
    1.59
     Chinois
    1.56
     épis
    1.56
    Activations Density 0.417%

    No Known Activations