© 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. 3398
    Prev
    Next
    INDEX
    Explanations

    statistics or numerical information related to various topics like government, economics, and health

    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
    +0.25
    1.3%
    1535
    +0.16
    0.8%
    2019
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.25
    0.25
    381
    +0.16
    0.10
    1535
    +0.15
    0.11
    Negative Logits
    <bos>
    -2.61
    ⓧ
    -1.39
     intersper
    -1.37
     hairc
    -1.25
    /***
    -1.22
     swarovski
    -1.17
     unve
    -1.17
     pessi
    -1.13
     quitted
    -1.11
     tupperware
    -1.10
    POSITIVE LOGITS
     cooperativa
    0.63
    pañ
    0.60
     cabina
    0.58
     tonel
    0.57
     membrana
    0.51
     lavander
    0.50
     udang
    0.50
    According
    0.50
     miniatura
    0.49
     marea
    0.49
    Activations Density 2.318%

    No Known Activations