© 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. 2586
    Prev
    Next
    INDEX
    Explanations

    references to intellectual property rights and legal terms related to trademarks and patents

    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
    +0.07
    0.2%
    1520
    +0.06
    0.2%
    1218
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.07
    0.02
    1359
    +0.06
    0.02
    1283
    +0.06
    0.02
    Negative Logits
    <bos>
    -1.29
    /*
    -0.85
    /**
    -0.80
    
    -0.80
    ⓧ
    -0.74
     springfox
    -0.71
    HasIndex
    -0.69
    <?
    -0.69
    #![
    -0.64
    <?
    -0.63
    POSITIVE LOGITS
     intellectual
    2.32
     Intellectual
    2.11
    intellectual
    2.04
    Intellectual
    2.02
     intellectually
    1.60
     intelectual
    1.57
     sappi
    1.38
     applau
    1.36
     intellect
    1.30
     tramont
    1.27
    Activations Density 0.066%

    No Known Activations