© 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. 199
    Prev
    Next
    INDEX
    Explanations

    descriptions of various items or products or lists of items

    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
    +0.24
    2.2%
    382
    +0.15
    1.4%
    2019
    +0.11
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.24
    0.40
    1535
    +0.15
    0.02
    2034
    +0.11
    0.29
    Negative Logits
    <bos>
    -2.07
    ⓧ
    -1.36
    
    -1.32
    /**
    -1.31
    <?
    -1.26
    /***
    -1.10
    /*
    -1.06
    ///**
    -1.04
    <?
    -1.01
     springfox
    -0.92
    POSITIVE LOGITS
     véhic
    0.70
     expériment
    0.69
     catég
    0.69
     marea
    0.67
     soulign
    0.65
     délib
    0.65
     nécess
    0.65
     allé
    0.63
     épu
    0.63
     alté
    0.60
    Activations Density 3.338%

    No Known Activations