© 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. 1637
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values or ratings

    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
    2019
    +0.32
    1.9%
    50
    +0.24
    1.5%
    1699
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.32
    0.12
    304
    +0.24
    0.01
    1699
    +0.12
    0.08
    Negative Logits
    <bos>
    -2.52
    /**
    -1.16
    ⓧ
    -1.16
    <?
    -1.09
     springfox
    -1.06
    
    -0.97
     quitted
    -0.88
     disbur
    -0.88
    /***
    -0.87
     unve
    -0.86
    POSITIVE LOGITS
     galeria
    0.73
     Metode
    0.69
     seksi
    0.64
     kafe
    0.63
     miniatura
    0.61
     keramik
    0.61
     sabun
    0.61
     mikrofon
    0.60
     Pagina
    0.60
     Formato
    0.60
    Activations Density 0.339%

    No Known Activations