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. 1798
    Prev
    Next
    INDEX
    Explanations

    periods or decimal points in numerical data

    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
    +0.32
    1.4%
    2019
    +0.13
    0.6%
    382
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.32
    0.05
    1445
    +0.13
    0.05
    382
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.01
     pessi
    -0.88
     quitted
    -0.87
     forbear
    -0.86
     intersper
    -0.81
     endow
    -0.81
     blest
    -0.74
     snapback
    -0.73
     gild
    -0.72
     fonder
    -0.72
    POSITIVE LOGITS
    Literat
    0.88
     praça
    0.79
     Aún
    0.77
     Tampoco
    0.72
     Hitam
    0.69
     seksi
    0.68
     Cerca
    0.68
     Estaba
    0.68
     Divulgação
    0.67
     Jusqu
    0.67
    Activations Density 0.211%

    No Known Activations