© 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. 7219
    Prev
    Next
    INDEX
    Explanations

    occurrences of words related to football turnovers and fumbles

    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
    +0.21
    0.7%
    946
    +0.09
    0.3%
    405
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1733
    +0.21
    0.03
    736
    +0.09
    0.04
    1553
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.24
    /***
    -0.72
    ///**
    -0.68
    intios
    -0.62
    build
    -0.62
    <tfoot>
    -0.62
    Autoritní
    -0.61
    MessageOf
    -0.59
    writeFieldEnd
    -0.58
    örös
    -0.58
    POSITIVE LOGITS
     maksi
    1.01
     seksi
    1.00
     kafe
    0.99
     panik
    0.97
     kaos
    0.96
     Meksi
    0.95
     lele
    0.94
     wattpad
    0.92
     carrefour
    0.91
     maroc
    0.91
    Activations Density 0.128%

    No Known Activations