© 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. 852
    Prev
    Next
    INDEX
    Explanations

    websites or links

    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
    +0.11
    0.4%
    783
    +0.07
    0.3%
    1438
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    631
    +0.11
    0.04
    1206
    +0.07
    0.04
    1691
    +0.06
    0.04
    Negative Logits
    <?
    -0.90
    /*
    -0.90
    /**
    -0.89
    ⓧ
    -0.86
    
    -0.79
     then
    -0.77
    ,
    -0.77
     expand
    -0.76
     could
    -0.76
     have
    -0.76
    POSITIVE LOGITS
     affor
    2.08
     maneu
    2.06
     délib
    2.01
     impra
    1.99
     accla
    1.89
     véhic
    1.88
     lidl
    1.88
     increa
    1.87
     unden
    1.86
     sappi
    1.78
    Activations Density 0.117%

    No Known Activations