Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 729
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    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
    +0.35
    1.6%
    2019
    +0.16
    0.7%
    382
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.35
    0.06
    1265
    +0.16
    0.05
    2019
    +0.13
    0.06
    Negative Logits
    <bos>
    -2.86
    qiao
    -0.67
     Paglinawan
    -0.63
    SPECTION
    -0.61
     zumal
    -0.61
    ⓧ
    -0.59
     springfox
    -0.59
    ostruct
    -0.58
    \}=\
    -0.58
    VERTIS
    -0.58
    POSITIVE LOGITS
     Juf
    1.37
     accla
    1.36
     affor
    1.24
     maneu
    1.18
     increa
    1.18
     intrigu
    1.13
     impra
    1.11
     reluct
    1.10
     unspeak
    1.10
     disgra
    1.10
    Activations Density 0.333%

    No Known Activations