© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 126
    Prev
    Next
    INDEX
    Explanations

    information related to historical figures and events, especially those in literature and science

    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
    +0.22
    1.9%
    2019
    +0.13
    1.1%
    1699
    +0.10
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.22
    0.07
    1699
    +0.13
    0.23
    1535
    +0.10
    0.02
    Negative Logits
    ⓧ
    -1.51
    <?
    -1.31
    
    
    -1.31
    /**
    -1.30
    <bos>
    -1.29
    <?
    
    -1.09
    /***
    
    -1.06
    /*
    -1.03
     springfox
    -0.93
    /*!
    
    -0.88
    POSITIVE LOGITS
     maneu
    1.27
     lele
    1.24
     maroc
    1.21
     affor
    1.19
     véhic
    1.15
     impra
    1.12
     Juf
    1.11
     accla
    1.10
     Intere
    1.08
     aen
    1.08
    Activations Density 2.478%

    No Known Activations