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. 25-GEMMASCOPE-RES-16K
    6. 6052
    Prev
    Next
    INDEX
    Explanations

    formal expressions related to political or governmental cooperation and initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whatever
    -0.64
    Whatever
    -0.62
    whatever
    -0.61
     revanche
    -0.60
     Whatever
    -0.57
     if
    -0.56
     qualunque
    -0.56
     unless
    -0.55
     sometimes
    -0.54
     وليس
    -0.54
    POSITIVE LOGITS
     congratulated
    0.94
     congratulate
    0.88
     congrat
    0.83
     thanked
    0.82
     graced
    0.81
     ceremony
    0.78
     thanking
    0.78
     Ceremony
    0.76
     dignitaries
    0.74
     inaugurated
    0.73
    Activations Density 0.148%

    No Known Activations