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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 246
    Prev
    Next
    INDEX
    Explanations

    numeric values indicating a result or outcome

    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
    +0.11
    0.4%
    528
    +0.05
    0.2%
    629
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1076
    +0.11
    0.03
    985
    +0.05
    0.03
    921
    +0.04
    0.03
    Negative Logits
    <bos>
    -1.59
    <!--
    -0.66
    //@
    -0.63
    ੇ
    -0.59
     onBind
    -0.58
    <tfoot>
    -0.57
    /**
    -0.57
    <!--<
    -0.57
    /*
    -0.57
    ///**
    -0.55
    POSITIVE LOGITS
     maneu
    1.95
     affor
    1.66
     accla
    1.62
     increa
    1.60
     disagre
    1.59
     shenan
    1.58
     gaily
    1.55
     lidl
    1.53
     impra
    1.52
     reluct
    1.51
    Activations Density 0.098%

    No Known Activations