© 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. 0-RES-JB
    11. 1351
    Prev
    Next
    INDEX
    Explanations

    data or file transfer - possibly related to speed and progress

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.21
    2.8%
    2019
    +0.12
    1.6%
    1699
    +0.09
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.21
    0.24
    1699
    +0.12
    0.16
    1967
    +0.09
    0.01
    Negative Logits
    <bos>
    -1.73
    ⓧ
    -1.41
    /**
    -1.33
    
    -1.26
    <?
    -1.26
    /*
    -1.08
    <?
    -1.02
     springfox
    -0.95
    /***
    -0.89
    ///**
    -0.83
    POSITIVE LOGITS
     maneu
    1.66
     affor
    1.60
     increa
    1.47
     véhic
    1.44
     accla
    1.39
     impra
    1.38
     Intere
    1.35
     Juf
    1.34
     inev
    1.33
     stockholm
    1.32
    Activations Density 2.014%

    No Known Activations