© 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. 7497
    Prev
    Next
    INDEX
    Explanations

    products and item descriptions from an online store

    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
    +0.26
    1.3%
    2034
    +0.20
    1.0%
    382
    +0.19
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.26
    0.24
    2034
    +0.20
    0.24
    1535
    +0.19
    0.12
    Negative Logits
    <bos>
    -2.60
    ⓧ
    -1.40
    /***
    -1.11
    
    -1.11
    /**
    -1.10
    ///**
    -1.00
     springfox
    -0.95
    Transcripción
    -0.93
    <?
    -0.93
    <tfoot>
    -0.91
    POSITIVE LOGITS
     épu
    0.99
     véhic
    0.90
     malheureux
    0.90
     maroc
    0.89
     déchir
    0.89
     soulign
    0.86
     écl
    0.84
     curieux
    0.84
     expériment
    0.83
     prét
    0.82
    Activations Density 2.380%

    No Known Activations