© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2895
    Prev
    Next
    INDEX
    Explanations

    terms related to the improvement and refinement of skills or practices

    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
    +0.15
    0.6%
    478
    +0.12
    0.5%
    1271
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    920
    +0.15
    0.03
    890
    +0.12
    0.03
    169
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.83
     intersper
    -1.09
     encomp
    -0.97
     disbur
    -0.87
     McLaugh
    -0.80
    /***
    -0.80
     McInt
    -0.76
     endow
    -0.74
     philanth
    -0.73
     Lorsqu
    -0.72
    POSITIVE LOGITS
     vasi
    0.92
     alpes
    0.90
     parati
    0.90
     marmor
    0.89
     riva
    0.89
     torba
    0.84
     alpina
    0.83
     Nieren
    0.82
     rheumat
    0.82
     palio
    0.82
    Activations Density 0.228%

    No Known Activations