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. 1029
    Prev
    Next
    INDEX
    Explanations

    references to the name "Maria" in various 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
    251
    +0.19
    1.1%
    1103
    +0.17
    0.9%
    1035
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.19
    0.02
    227
    +0.17
    0.03
    1983
    +0.15
    0.02
    Negative Logits
    <bos>
    -0.96
    脚注の使い方
    -0.69
     كومونز
    -0.64
    LookAnd
    -0.58
    pidou
    -0.56
    ContentLoaded
    -0.56
    PerformLayout
    -0.56
    ItemBackground
    -0.55
     sanit
    -0.55
    setVerticalGroup
    -0.54
    POSITIVE LOGITS
     Maria
    1.61
    Maria
    1.57
    MARIA
    1.20
     maria
    1.18
     MARIA
    1.17
     María
    1.11
    maria
    1.09
    María
    0.95
     Jusqu
    0.95
     montrant
    0.94
    Activations Density 0.137%

    No Known Activations