© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 316
    Prev
    Next
    INDEX
    Explanations

    mentions of music-related words, such as "album," "song," "concerts," and "rock."

    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
    +0.15
    0.8%
    1385
    +0.06
    0.4%
    1870
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.15
    0.27
    1870
    +0.06
    0.04
    491
    +0.04
    0.11
    Negative Logits
    <bos>
    -2.83
    HasAnnotation
    -0.84
    ⓧ
    -0.84
    /***
    -0.77
    //{
    -0.76
    ുറ
    -0.75
     of
    -0.73
    #![
    -0.71
    /**
    -0.70
     springfox
    -0.69
    POSITIVE LOGITS
     bandung
    1.73
     affor
    1.68
     véhic
    1.66
     haup
    1.62
     maneu
    1.61
     impra
    1.57
     napoli
    1.57
     increa
    1.57
     maroc
    1.56
     Intere
    1.55
    Activations Density 4.585%

    No Known Activations