© 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. 10-RES-JB
    11. 4708
    Prev
    Next
    INDEX
    Explanations

    specific measurements and physical dimensions related to athletes

    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
    50
    +0.23
    0.9%
    814
    +0.08
    0.3%
    1385
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1841
    +0.23
    0.03
    858
    +0.08
    0.03
    1302
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.04
     intersper
    -1.50
     encomp
    -1.31
    
    -1.19
    ⓧ
    -1.14
    /**
    -1.05
     quitted
    -1.05
     gild
    -0.96
     defray
    -0.95
     disbur
    -0.95
    POSITIVE LOGITS
     tall
    0.69
     Potosí
    0.67
     height
    0.64
    UIFont
    0.61
    height
    0.61
    ydın
    0.60
     cioc
    0.58
     Morelos
    0.58
     Vallarta
    0.57
    getHeight
    0.57
    Activations Density 0.040%

    No Known Activations