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. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3836
    Prev
    Next
    INDEX
    Explanations

    contrastive statements or qualifications in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mero
    -0.99
     Dorian
    -0.96
    ſelf
    -0.92
     xenia
    -0.89
     gie
    -0.88
     Yerevan
    -0.87
     Nemo
    -0.87
     $_"
    -0.87
     NEO
    -0.86
     Nara
    -0.86
    POSITIVE LOGITS
     But
    1.81
     but
    1.62
    but
    1.47
     BUT
    1.46
    But
    1.46
    BUT
    1.24
     pero
    1.16
     nhưng
    0.94
     แต่
    0.90
    但
    0.90
    Activations Density 0.132%

    No Known Activations