© 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. 3480
    Prev
    Next
    INDEX
    Explanations

    comparisons between different quantities or values in financial or statistical contexts

    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
    776
    +0.11
    0.4%
    257
    +0.11
    0.4%
    1535
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.11
    0.06
    1055
    +0.11
    0.05
    257
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.85
    Демографія
    -0.71
    Vegeu
    -0.69
    ⓧ
    -0.68
    Huhu
    -0.67
    <?
    -0.67
    contentLoaded
    -0.66
    Зміст
    -0.64
     nela
    -0.64
     Justo
    -0.63
    POSITIVE LOGITS
    dirond
    0.83
     chré
    0.79
     pank
    0.75
     Désolé
    0.75
     asos
    0.75
     saati
    0.73
     sué
    0.72
     mcdonald
    0.72
     mikrofon
    0.71
     tatou
    0.71
    Activations Density 0.641%

    No Known Activations