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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6662
    Prev
    Next
    INDEX
    Explanations

    references to large quantities, particularly in financial or measurement contexts

    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
    +0.25
    0.8%
    297
    +0.10
    0.3%
    1013
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.25
    0.08
    297
    +0.10
    0.07
    1036
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.17
     intptr
    -0.71
     lutar
    -0.67
     ExecuteAsync
    -0.66
     hiel
    -0.64
     ProtoMessage
    -0.63
     tenden
    -0.62
     reag
    -0.62
     impon
    -0.61
     rech
    -0.60
    POSITIVE LOGITS
     churrasco
    0.85
     nutella
    0.80
     Alcalde
    0.76
     bandung
    0.75
     Compañ
    0.74
     Hitam
    0.72
     soulign
    0.70
     tupperware
    0.69
     ecru
    0.69
     Putih
    0.69
    Activations Density 0.458%

    No Known Activations