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. 6775
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and their frequency

    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
    +0.20
    0.7%
    382
    +0.15
    0.5%
    1535
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.20
    0.05
    562
    +0.15
    0.04
    464
    +0.14
    0.04
    Negative Logits
    <bos>
    -2.59
     intersper
    -1.75
     shenan
    -1.58
    /**
    -1.50
     pamph
    -1.50
     rascal
    -1.48
    
    
    -1.47
     hairc
    -1.45
    ⓧ
    -1.45
     unspeak
    -1.43
    POSITIVE LOGITS
     mikrofon
    0.88
     karton
    0.76
     kosme
    0.75
     akus
    0.75
     gesta
    0.74
     alkoh
    0.73
     silikon
    0.73
     kompres
    0.72
     utop
    0.71
     optik
    0.71
    Activations Density 0.190%

    No Known Activations