© 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. 1010
    Prev
    Next
    INDEX
    Explanations

    phrases related to the immune system and medical terminology

    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
    +0.20
    1.2%
    2019
    +0.07
    0.4%
    1156
    +0.05
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.20
    0.10
    1334
    +0.07
    0.10
    897
    +0.05
    0.09
    Negative Logits
    <bos>
    -2.81
    ⓧ
    -1.36
    <?
    -1.19
    /**
    -1.19
    
    -1.16
    <?
    -1.01
    /*
    -0.96
    /*++
    -0.86
    /***
    -0.84
    /*!
    -0.81
    POSITIVE LOGITS
     maneu
    1.42
     Juf
    1.39
     stockholm
    1.37
     affor
    1.37
     aen
    1.35
     maroc
    1.33
     hcm
    1.33
     véhic
    1.32
     wien
    1.29
     accla
    1.27
    Activations Density 1.223%

    No Known Activations