© 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. 6-RES-JB
    11. 6946
    Prev
    Next
    INDEX
    Explanations

    names of professionals or experts

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.14
    0.8%
    168
    +0.13
    0.8%
    1271
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.10
    227
    +0.13
    0.13
    1097
    +0.11
    0.12
    Negative Logits
    <bos>
    -2.50
    <?
    -0.90
    /***
    -0.87
    /*!
    -0.69
     CascadeType
    -0.64
    <!--
    -0.63
    šech
    -0.63
    ⓧ
    -0.62
    HasIndex
    -0.59
     /**
    -0.57
    POSITIVE LOGITS
     increa
    1.38
     impra
    1.35
     maneu
    1.29
     inev
    1.29
     affor
    1.25
     accla
    1.23
     ftu
    1.23
     thut
    1.21
     aen
    1.21
     effe
    1.20
    Activations Density 1.528%

    No Known Activations