© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 523
    Prev
    Next
    INDEX
    Explanations

    references to actions and events related to a sports game, specifically football, including mentions of specific players, plays, and outcomes

    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
    +0.12
    0.5%
    1842
    +0.08
    0.3%
    956
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.12
    0.02
    956
    +0.08
    0.07
    1703
    +0.05
    0.07
    Negative Logits
    <bos>
    -1.18
    ///**
    -0.75
    //{
    -0.74
    public
    -0.71
    <?
    -0.70
    ///////////////
    -0.69
    /***
    -0.69
    //
    -0.69
    //{
    -0.68
    //--
    -0.67
    POSITIVE LOGITS
     maneu
    1.85
     affor
    1.83
     impra
    1.71
     increa
    1.63
     scrat
    1.53
     reluct
    1.51
     shenan
    1.50
     snoopy
    1.49
     accla
    1.49
     stockholm
    1.49
    Activations Density 2.461%

    No Known Activations