© 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 EvalsExportsinterp-engineNEWAPI 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. 4668
    Prev
    Next
    INDEX
    Explanations

    information related to copper materials or elements

    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
    1520
    +0.13
    0.6%
    61
    +0.12
    0.5%
    795
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1520
    +0.13
    0.02
    981
    +0.12
    0.03
    1971
    +0.12
    0.02
    Negative Logits
     pylab
    -0.71
     smtplib
    -0.59
     pymongo
    -0.53
    ristiana
    -0.53
     câte
    -0.53
     potrivit
    -0.53
     fratelli
    -0.52
     hashlib
    -0.51
     fidanz
    -0.51
    asserole
    -0.51
    POSITIVE LOGITS
     Cu
    1.31
    Cu
    1.26
     cu
    1.25
    cu
    1.19
     CU
    1.14
    CU
    1.02
     copper
    0.91
     Ku
    0.88
    copper
    0.86
     Cuomo
    0.85
    Activations Density 0.120%

    No Known Activations