© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2617
    Prev
    Next
    INDEX
    Explanations

    structured patterns such as numbered lists

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.14
    0.5%
    871
    +0.07
    0.2%
    947
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    871
    +0.14
    0.02
    808
    +0.07
    0.02
    856
    +0.06
    0.03
    Negative Logits
    ⓧ
    -0.86
    /**
    -0.85
    
    -0.80
    <?
    -0.78
    /***
    -0.75
    ///**
    -0.74
    /*
    -0.67
    <bos>
    -0.66
     sabem
    -0.62
     eradicate
    -0.59
    POSITIVE LOGITS
     Kategor
    1.30
     maneu
    1.28
     incess
    1.27
     lele
    1.23
     plak
    1.23
     alkoh
    1.22
     Telex
    1.21
     stockholm
    1.21
     elek
    1.21
     karton
    1.21
    Activations Density 0.076%

    No Known Activations