© 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. 1529
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific and experimental concepts

    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
    1705
    +0.18
    0.7%
    878
    +0.14
    0.5%
    1379
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.18
    0.08
    1870
    +0.14
    0.05
    1385
    +0.13
    0.09
    Negative Logits
    <bos>
    -1.70
    ↵↵
    -0.82
     &
    -0.70
    ↵↵↵
    -0.69
     a
    -0.68
     (
    -0.67
    ↵
    -0.66
    .
    -0.66
     A
    -0.66
    ↵↵↵↵
    -0.65
    POSITIVE LOGITS
     soggior
    1.89
     swarovski
    1.67
     affez
    1.63
     paillettes
    1.56
     sappi
    1.51
     Moderato
    1.47
     fatis
    1.47
     hecta
    1.47
     soste
    1.44
     appunt
    1.44
    Activations Density 1.002%

    No Known Activations