© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2385
    Prev
    Next
    INDEX
    Explanations

    interjections and expressions of surprise or excitement

    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
    +0.37
    2.1%
    2019
    +0.18
    1.0%
    1577
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.37
    0.32
    1535
    +0.18
    0.22
    1445
    +0.12
    0.25
    Negative Logits
    <bos>
    -1.96
    ⓧ
    -1.22
    <?
    -1.07
    /***
    -1.05
    /**
    -1.04
    
    -1.03
     springfox
    -0.98
     quitted
    -0.88
     chande
    -0.84
    Transkript
    -0.83
    POSITIVE LOGITS
     marea
    0.58
    ↵↵
    0.54
     Presenta
    0.51
    mamp
    0.50
    laris
    0.50
    <em>
    0.50
    Rng
    0.49
    <i>
    0.49
    cadi
    0.47
    <b>
    0.47
    Activations Density 1.797%

    No Known Activations