© 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. 1999
    Prev
    Next
    INDEX
    Explanations

    structured data or numerical patterns, particularly in relation to demographics

    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
    +0.18
    0.8%
    2019
    +0.17
    0.8%
    1177
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1699
    +0.18
    0.04
    1343
    +0.17
    0.04
    1445
    +0.14
    0.04
    Negative Logits
    <bos>
    -3.65
    /**
    -1.37
    
    -1.25
    <?
    -1.21
    ⓧ
    -1.14
    /*
    -1.12
     intersper
    -1.00
     endow
    -0.85
     disbur
    -0.84
     quitted
    -0.84
    POSITIVE LOGITS
     utop
    1.11
     apparti
    1.09
     elef
    1.05
     manuten
    1.04
     ortop
    1.02
     incess
    1.02
     vola
    1.01
     hunde
    1.01
     bandung
    0.99
     ananas
    0.99
    Activations Density 0.159%

    No Known Activations