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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 777
    Prev
    Next
    INDEX
    Explanations

    numeric values and their associations in the context of data

    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
    +0.24
    0.8%
    1614
    +0.09
    0.3%
    1741
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1614
    +0.24
    0.08
    776
    +0.09
    0.08
    499
    +0.08
    0.07
    Negative Logits
    <bos>
    -1.96
    ArgumentParser
    -0.71
    blurRadius
    -0.71
    HasIndex
    -0.67
    BuildContext
    -0.66
    DataMember
    -0.65
    HasAnnotation
    -0.64
    displayquote
    -0.64
    addWidget
    -0.63
    TagHelper
    -0.62
    POSITIVE LOGITS
     maneu
    1.87
     Juf
    1.65
     impra
    1.61
     increa
    1.59
     affor
    1.57
     milf
    1.56
     bandung
    1.56
     napoli
    1.50
     🤣🤣
    1.50
     shenan
    1.48
    Activations Density 0.398%

    No Known Activations