© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7711
    Prev
    Next
    INDEX
    Explanations

    numerical values preceded by the word "can" and "could" in sentences

    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
    +0.22
    0.9%
    966
    +0.10
    0.4%
    1008
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.22
    0.04
    966
    +0.10
    0.05
    1634
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.38
    /***
    -0.69
    
    -0.66
    ///**
    -0.65
    /**
    -0.57
    <?
    -0.55
    EndProject
    -0.55
    <?
    -0.54
    šech
    -0.54
    Kontrola
    -0.53
    POSITIVE LOGITS
     kaos
    1.39
     saar
    1.36
     kafe
    1.29
     maske
    1.26
     lele
    1.25
     maksi
    1.24
     silikon
    1.24
     kram
    1.24
     tyn
    1.22
     seksi
    1.22
    Activations Density 0.436%

    No Known Activations