© 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. 6005
    Prev
    Next
    INDEX
    Explanations

    references to service providers and licensing details

    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
    1870
    +0.13
    0.7%
    1092
    +0.12
    0.7%
    50
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.13
    0.03
    1092
    +0.12
    0.02
    1507
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.82
    ⓧ
    -0.88
    
    -0.64
     springfox
    -0.62
     يتيمه
    -0.59
    <?
    -0.57
    <?
    -0.57
    ///**
    -0.57
    Ша
    -0.56
    /**
    -0.55
    POSITIVE LOGITS
     Provider
    1.35
     provider
    1.33
     Providers
    1.30
     providers
    1.24
    provider
    1.19
    Provider
    1.12
    providers
    1.09
     alha
    1.09
     Traité
    1.08
     saar
    1.07
    Activations Density 0.113%

    No Known Activations