© 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. 1742
    Prev
    Next
    INDEX
    Explanations

    numbers on sports-related plays

    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
    +0.14
    0.8%
    1871
    +0.04
    0.2%
    678
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.22
    283
    +0.04
    0.06
    1871
    +0.04
    0.06
    Negative Logits
    <bos>
    -1.98
    ,
    -0.98
    .
    -0.92
    
    -0.92
     also
    -0.88
     continue
    -0.86
     for
    -0.86
     put
    -0.85
     can
    -0.84
     be
    -0.84
    POSITIVE LOGITS
     saar
    1.90
     maroc
    1.82
     meis
    1.81
     wien
    1.76
     stockholm
    1.75
     lele
    1.74
     Minang
    1.72
     lidl
    1.71
     ananas
    1.68
     franz
    1.66
    Activations Density 1.632%

    No Known Activations