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. 6802
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those that pertain to dates and quantities

    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
    +0.29
    1.1%
    1741
    +0.09
    0.3%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1439
    +0.29
    0.04
    589
    +0.09
    0.03
    1188
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.63
    ⓧ
    -1.25
     intersper
    -1.24
     encomp
    -1.22
     quitted
    -1.20
    <?
    
    -1.05
    <?
    -1.02
    /**
    -1.02
     hairc
    -0.99
    
    
    -0.97
    POSITIVE LOGITS
     Colección
    0.57
     Embaj
    0.54
     Notícias
    0.53
    Sklici
    0.53
     Princesa
    0.51
     Nacionales
    0.51
     Estación
    0.50
     Portugu
    0.50
     Compañía
    0.49
     Mulher
    0.49
    Activations Density 0.054%

    No Known Activations