© 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. 1723
    Prev
    Next
    INDEX
    Explanations

    information related to sports achievements and accolades, particularly in the context of soccer

    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
    1579
    +0.08
    0.2%
    1441
    +0.07
    0.2%
    10
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.02
    1579
    +0.07
    0.02
    1343
    +0.07
    0.03
    Negative Logits
    ⓧ
    -0.83
    JAKARTA
    -0.81
    /*
    -0.79
    Witam
    -0.73
    makeatletter
    -0.71
    theoremstyle
    -0.70
    /**
    -0.70
    #
    -0.68
    //
    -0.67
    <?
    -0.66
    POSITIVE LOGITS
    lets
    2.16
    let
    2.03
     meis
    1.73
    LET
    1.72
     effe
    1.69
     saar
    1.63
     daz
    1.63
     wien
    1.63
     aen
    1.62
     ?...
    1.61
    Activations Density 0.217%

    No Known Activations