Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 748
    Prev
    Next
    INDEX
    Explanations

    references to court rulings and legal decisions

    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
    +0.26
    1.0%
    1499
    +0.11
    0.4%
    499
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.26
    0.06
    499
    +0.11
    0.05
    1493
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.87
    ⓧ
    -0.68
     AssemblyCompany
    -0.63
    GENERATED
    -0.61
    fflush
    -0.59
    
    
    -0.57
    <?
    -0.56
    else
    -0.56
     يتيمه
    -0.56
    WriteLiteral
    -0.56
    POSITIVE LOGITS
     Minang
    1.50
     maneu
    1.46
     Juf
    1.34
     kasa
    1.28
     Karang
    1.24
     Pekan
    1.21
     Banjar
    1.21
     Khart
    1.20
     shenan
    1.18
     stockholm
    1.18
    Activations Density 0.466%

    No Known Activations