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. 109681
    Prev
    Next
    INDEX
    Explanations

    the phrase "get" in various contexts and its frequency within the text

    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
     get
    -0.45
     gets
    -0.38
     Fontana
    -0.36
     Hot
    -0.36
     got
    -0.34
    Token
    -0.33
    get
    -0.32
     Token
    -0.32
    H
    -0.31
    InputTagHelper
    -0.31
    POSITIVE LOGITS
    Personendaten
    0.76
     يتيمه
    0.74
     للمعارف
    0.68
    rungsseite
    0.66
    :✨
    0.65
    Autoritní
    0.64
    styleType
    0.64
    ScopeManager
    0.62
     referenties
    0.61
     المعيارى
    0.61
    Activations Density 0.004%

    No Known Activations