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. 1819
    Prev
    Next
    INDEX
    Explanations

    references to upcoming events or milestones related to time periods

    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
    453
    +0.20
    0.9%
    776
    +0.10
    0.5%
    964
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.20
    0.04
    1036
    +0.10
    0.02
    304
    +0.10
    -0.01
    Negative Logits
    <bos>
    -3.03
     Italijani
    -0.87
     Administrativna
    -0.83
    ⓧ
    -0.81
    contentLoaded
    -0.79
    /**
    -0.77
     EconPapers
    -0.72
    AsUp
    -0.71
    Autoritní
    -0.71
     Italijanski
    -0.69
    POSITIVE LOGITS
     beverly
    0.57
     Etr
    0.57
     erik
    0.56
     vété
    0.55
     AppBundle
    0.54
     habile
    0.54
     éner
    0.54
     curieux
    0.54
    $($
    0.53
     mika
    0.52
    Activations Density 0.173%

    No Known Activations