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. 1077
    Prev
    Next
    INDEX
    Explanations

    references to daily publications or news outlets

    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
    +0.22
    1.2%
    241
    +0.15
    0.8%
    897
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.22
    0.04
    1895
    +0.15
    0.03
    1335
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.74
    mfenced
    -0.67
    <!--
    
    -0.65
     initComponents
    -0.64
    itemize
    -0.63
    <!--[
    -0.63
    ComponentModel
    -0.62
    MergeFrom
    -0.61
     put
    -0.61
     believe
    -0.61
    POSITIVE LOGITS
     Juf
    1.78
     Minang
    1.71
     increa
    1.70
     lele
    1.69
     Intere
    1.69
     maneu
    1.67
     lidl
    1.65
     milano
    1.64
     wien
    1.62
     affor
    1.62
    Activations Density 0.040%

    No Known Activations