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. 897
    Prev
    Next
    INDEX
    Explanations

    details about community events and activities

    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
    1.5%
    1013
    +0.14
    0.6%
    678
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1403
    +0.35
    0.02
    1013
    +0.14
    0.07
    678
    +0.14
    0.06
    Negative Logits
    <bos>
    -0.93
    /*
    -0.79
    const
    -0.76
    
    
    -0.75
    /**
    -0.75
    append
    -0.74
    XmlAccessType
    -0.73
    margin
    -0.72
    [
    -0.72
    delete
    -0.72
    POSITIVE LOGITS
     reluct
    2.47
     maneu
    2.41
     accla
    2.39
     impra
    2.34
     depic
    2.27
     affor
    2.25
     guarante
    2.24
     increa
    2.23
     Keny
    2.20
     uniqu
    2.17
    Activations Density 0.699%

    No Known Activations