© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 382
    Prev
    Next
    INDEX
    Explanations

    concepts related to economic cycles and self-fulfilling prophecies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.19
    0.7%
    1705
    +0.09
    0.3%
    1622
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.19
    0.04
    1867
    +0.09
    0.06
    1363
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.44
    ToListAsync
    -0.61
    <!--
    -0.60
     designate
    -0.57
     included
    -0.54
    public
    -0.54
     AssemblyTitle
    -0.53
    /***
    -0.52
     and
    -0.52
     respectively
    -0.52
    POSITIVE LOGITS
     soggior
    1.35
     😭😭
    1.15
     mondeo
    1.15
     swarovski
    1.14
     particolar
    1.13
     ragion
    1.10
     🤣🤣
    1.09
     🥲
    1.08
     paradiso
    1.08
     oleo
    1.07
    Activations Density 0.504%

    No Known Activations