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. 778
    Prev
    Next
    INDEX
    Explanations

    terms related to water resources and management

    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
    +0.27
    1.1%
    1870
    +0.12
    0.5%
    1967
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.27
    0.10
    1870
    +0.12
    0.07
    908
    +0.11
    0.06
    Negative Logits
    <bos>
    -2.84
    GEBURTSDATUM
    -1.14
    Билгалдахарш
    -0.92
    DeleteBehavior
    -0.88
     autorytatywna
    -0.87
     kasarigan
    -0.84
    fjspx
    -0.81
    ⓧ
    -0.81
    商品説明
    -0.78
    الإنجليزية
    -0.76
    POSITIVE LOGITS
     Minang
    1.61
     bandung
    1.54
     lele
    1.54
     jawa
    1.53
     saar
    1.52
     jati
    1.48
     keramik
    1.47
     kasa
    1.45
     jaya
    1.43
     teras
    1.42
    Activations Density 0.602%

    No Known Activations