© 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. 0-RES-JB
    11. 1183
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Le" or "Le9" preceded by symbols

    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%
    1805
    +0.07
    0.2%
    1141
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1615
    +0.10
    0.03
    954
    +0.07
    0.03
    252
    +0.07
    0.03
    Negative Logits
     Aussi
    -0.73
    public
    -0.68
    
    -0.67
     Autre
    -0.65
     maintain
    -0.65
     Toujours
    -0.63
     Beaucoup
    -0.63
     strengthen
    -0.62
    else
    -0.62
     overcome
    -0.61
    POSITIVE LOGITS
     Le
    2.40
    Le
    2.12
     le
    1.76
     effe
    1.66
     levis
    1.66
     lein
    1.65
     habile
    1.64
     accla
    1.64
     maneu
    1.58
     sovere
    1.58
    Activations Density 0.177%

    No Known Activations