© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3278
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions

    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
    +0.18
    0.9%
    1506
    +0.16
    0.8%
    517
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1506
    +0.18
    0.06
    630
    +0.16
    0.05
    517
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.98
    //{
    -0.70
     serve
    -0.68
    /***
    -0.66
    //@
    -0.62
     introduce
    -0.62
     expose
    -0.61
    /*!
    -0.60
    ുറ
    -0.60
     expand
    -0.59
    POSITIVE LOGITS
     stockholm
    1.49
     jaya
    1.42
     lidl
    1.35
     ankara
    1.31
     kyo
    1.30
     shopee
    1.30
     madonna
    1.29
     ibiza
    1.27
     bandung
    1.26
     uniqlo
    1.25
    Activations Density 0.281%

    No Known Activations