© 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. 7778
    Prev
    Next
    INDEX
    Explanations

    mentions of competitive sports events

    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
    +0.38
    2.4%
    1967
    +0.15
    1.0%
    1984
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.38
    0.17
    1896
    +0.15
    0.11
    1034
    +0.12
    0.11
    Negative Logits
    <bos>
    -3.02
    //};
    -0.78
    };*/
    -0.74
    ⓧ
    -0.73
    //});
    -0.72
    //----
    -0.71
    ///**
    -0.69
    /***
    -0.69
    //---
    -0.69
    //*/
    -0.67
    POSITIVE LOGITS
     véhic
    0.97
     viciss
    0.96
     valencia
    0.95
     marea
    0.92
     sappi
    0.89
     conflic
    0.88
     Compañ
    0.86
     Haci
    0.86
     soulign
    0.85
     quoique
    0.81
    Activations Density 1.056%

    No Known Activations