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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109706
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, particularly siblings and brotherhood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sister
    -1.16
     Brother
    -1.13
    Sister
    -1.07
    Brother
    -1.05
     BROTHER
    -0.73
     Brotherhood
    -0.55
     Bro
    -0.48
     Sisters
    -0.47
     Brothers
    -0.46
     bro
    -0.44
    POSITIVE LOGITS
    rungsseite
    0.63
     myſelf
    0.62
    verwijspagina
    0.61
    ⪜
    0.60
    Архівовано
    0.60
    AutoScaleMode
    0.58
     Anſ
    0.57
    קישורים
    0.56
    IntoConstraints
    0.56
     queſta
    0.56
    Activations Density 0.001%

    No Known Activations