© 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. 10-RES-JB
    11. 1564
    Prev
    Next
    INDEX
    Explanations

    words that relate to music or musical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    303
    +0.15
    0.6%
    369
    +0.14
    0.6%
    239
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.15
    0.08
    1363
    +0.14
    0.06
    1987
    +0.13
    0.05
    Negative Logits
    <bos>
    -1.70
    /**
    -0.73
    bardziej
    -0.72
    Díky
    -0.71
    Сол
    -0.69
     try
    -0.68
    Při
    -0.68
    Vlastnosti
    -0.66
     on
    -0.66
    Pře
    -0.66
    POSITIVE LOGITS
     aen
    1.85
     squa
    1.83
     fortn
    1.78
     fta
    1.76
     seiz
    1.75
     simplif
    1.74
     mef
    1.71
     thut
    1.71
     emphat
    1.71
     oner
    1.70
    Activations Density 0.370%

    No Known Activations