© 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. 1052
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, intellectual property, and legal disputes

    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
    +0.10
    0.4%
    1828
    +0.06
    0.2%
    1124
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1752
    +0.10
    0.04
    723
    +0.06
    0.03
    1888
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.23
    ⓧ
    -0.80
    <?
    -0.77
    /**
    -0.72
    
    -0.71
     knelt
    -0.70
    ുറ
    -0.69
    šech
    -0.68
    <tfoot>
    -0.65
    /*++
    -0.64
    POSITIVE LOGITS
     inter
    2.21
     Inter
    2.04
     Intere
    2.01
    Inter
    1.91
     intere
    1.71
    inter
    1.70
     INTER
    1.64
     inters
    1.57
     intermitt
    1.55
    INTER
    1.50
    Activations Density 0.084%

    No Known Activations