© 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. 6-RES-JB
    11. 3450
    Prev
    Next
    INDEX
    Explanations

    terms related to bacteria, viruses, infections, and medication

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.19
    0.8%
    144
    +0.11
    0.5%
    866
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.19
    0.03
    1809
    +0.11
    0.03
    1529
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.73
    ⓧ
    -0.67
    HideFlags
    -0.67
    EndProject
    -0.59
    HasBeenSet
    -0.55
     retires
    -0.55
    //---
    -0.53
    <tfoot>
    -0.51
    webElementXpaths
    -0.51
    /*---
    -0.51
    POSITIVE LOGITS
     thut
    1.37
     carrefour
    1.29
     bandung
    1.27
     naer
    1.27
     bourg
    1.22
     lele
    1.20
     jawa
    1.18
     Minang
    1.17
     ftu
    1.16
     saad
    1.16
    Activations Density 0.127%

    No Known Activations