© 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. 1329
    Prev
    Next
    INDEX
    Explanations

    quotations attributed to speakers in a dialogue format

    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
    +0.22
    0.8%
    906
    +0.12
    0.4%
    630
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    888
    +0.22
    0.05
    1445
    +0.12
    0.05
    1150
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.33
     intersper
    -0.91
    /***
    -0.91
     endow
    -0.86
    ⓧ
    -0.85
     swarovski
    -0.84
     quitted
    -0.80
     impractica
    -0.78
     liberality
    -0.78
     Ename
    -0.78
    POSITIVE LOGITS
     kosme
    1.16
     kooper
    1.00
     minimalis
    1.00
     akus
    0.99
     konkre
    0.99
     akade
    0.98
     induk
    0.96
     kriminal
    0.95
     protokol
    0.95
     praktik
    0.93
    Activations Density 0.249%

    No Known Activations