© 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. 2034
    Prev
    Next
    INDEX
    Explanations

    references related to diamonds and jewelry

    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
    871
    +0.13
    0.5%
    32
    +0.13
    0.5%
    479
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1335
    +0.13
    0.03
    1622
    +0.13
    0.02
    1512
    +0.12
    0.02
    Negative Logits
     hairc
    -0.82
     swarovski
    -0.82
     ecru
    -0.81
     beaute
    -0.78
     Ename
    -0.78
     unspeak
    -0.75
     linden
    -0.73
     cushi
    -0.72
     tolerably
    -0.72
     unlaw
    -0.71
    POSITIVE LOGITS
     Diamond
    1.06
     diamond
    1.05
    Diamond
    1.03
    diamond
    1.02
     crystal
    0.98
     gem
    0.97
    Crystal
    0.96
     diamonds
    0.96
     Crystal
    0.95
    crystal
    0.93
    Activations Density 0.126%

    No Known Activations