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-2-2B
    4. MLP Out - 16k
    5. 1-GEMMASCOPE-MLP-16K
    6. 8810
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "ran" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ran
    -2.22
    Ran
    -1.88
     Ran
    -1.83
    ran
    -1.45
     RAN
    -1.27
    RAN
    -1.16
    ranch
    -0.79
    хьтан
    -0.79
     ranch
    -0.78
     TextAppearance
    -0.78
    POSITIVE LOGITS
     darbu
    0.47
     mukana
    0.45
     aikana
    0.43
     abbraccio
    0.42
    writeFieldEnd
    0.41
     setempat
    0.40
     regler
    0.40
     Peker
    0.40
     humeur
    0.38
     تابع
    0.38
    Activations Density 0.258%

    No Known Activations