© 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. 1579
    Prev
    Next
    INDEX
    Explanations

    statements about player performance and evaluation

    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
    +0.27
    1.0%
    599
    +0.12
    0.5%
    381
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.27
    0.07
    599
    +0.12
    0.09
    1501
    +0.09
    0.07
    Negative Logits
    <bos>
    -1.41
     encomp
    -1.17
    ⓧ
    -1.15
     [''
    -1.10
     stratigraph
    -1.10
     Whence
    -1.09
     unve
    -1.08
     squa
    -1.03
     chery
    -1.02
     paula
    -1.02
    POSITIVE LOGITS
     balon
    0.97
     kaos
    0.93
     krim
    0.90
     parati
    0.88
     marea
    0.84
     torba
    0.83
     plastik
    0.82
     bronz
    0.81
     Teknik
    0.79
     tyn
    0.78
    Activations Density 0.680%

    No Known Activations