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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 205
    Prev
    Next
    INDEX
    Explanations

    descriptions related to facilities and services offered by a business

    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
    +0.25
    2.8%
    2019
    +0.12
    1.3%
    382
    +0.11
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.25
    0.34
    382
    +0.12
    0.36
    2034
    +0.11
    0.28
    Negative Logits
    <bos>
    -2.92
    ⓧ
    -1.36
    <?
    -1.23
    
    -1.22
    /**
    -1.18
    /***
    -1.11
    <?
    -1.05
    /*
    -0.98
    ///**
    -0.97
     springfox
    -0.86
    POSITIVE LOGITS
     maneu
    1.10
     affor
    0.96
     accla
    0.93
     véhic
    0.92
     Juf
    0.92
     catég
    0.91
     impra
    0.90
     délib
    0.85
     increa
    0.85
     expériment
    0.84
    Activations Density 3.672%

    No Known Activations