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. 6764
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to programming and data processing

    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
    +0.19
    0.8%
    227
    +0.13
    0.5%
    876
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.19
    0.01
    1871
    +0.13
    0.04
    304
    +0.13
    0.00
    Negative Logits
    <bos>
    -3.05
    ⓧ
    -1.10
    <?
    -0.90
    
    
    -0.87
    /**
    -0.86
    /*
    -0.82
     serve
    -0.80
     might
    -0.77
     слу
    -0.76
     can
    -0.76
    POSITIVE LOGITS
     napoli
    2.08
     bordeaux
    2.02
     wien
    2.00
     milano
    1.95
     applau
    1.91
     maroc
    1.90
     cannes
    1.90
     aen
    1.89
     bandung
    1.88
     dises
    1.85
    Activations Density 0.127%

    No Known Activations