© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4946
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistics related to quantities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    0.9%
    1385
    +0.14
    0.5%
    1978
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.24
    0.09
    776
    +0.14
    0.08
    1905
    +0.14
    0.06
    Negative Logits
    <bos>
    -2.79
     intersper
    -0.97
    ⓧ
    -0.86
    /***
    -0.79
     rouse
    -0.78
     overcrow
    -0.77
     endow
    -0.74
     inaugurate
    -0.73
     springfox
    -0.71
     harmonize
    -0.71
    POSITIVE LOGITS
     marea
    1.04
     Palembang
    0.93
     Bekasi
    0.92
     Tangerang
    0.91
     migli
    0.89
     silikon
    0.89
     uhr
    0.89
     monaster
    0.88
     saar
    0.88
     karton
    0.87
    Activations Density 0.264%

    No Known Activations