© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1321
    Prev
    Next
    INDEX
    Explanations

    discussions about varying circumstances or situations

    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
    +0.21
    0.8%
    1994
    +0.10
    0.4%
    896
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.21
    0.04
    814
    +0.10
    0.04
    1820
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.15
    fetch
    -0.67
    Dura
    -0.66
    Dire
    -0.65
    public
    -0.65
    lim
    -0.64
    protected
    -0.64
    ///**
    -0.63
    auto
    -0.62
    Uso
    -0.62
    POSITIVE LOGITS
     milf
    1.49
     chrysler
    1.42
     maneu
    1.40
     jaya
    1.40
     pixar
    1.36
     jurassic
    1.33
     snoopy
    1.33
     panama
    1.32
     yoda
    1.31
     hentai
    1.31
    Activations Density 0.251%

    No Known Activations