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. 10312
    Prev
    Next
    INDEX
    Explanations

    references to marine wildlife interactions and diving activities

    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
    RuleContext
    -0.57
     ferrovia
    -0.52
     powi
    -0.51
     للاسماء
    -0.50
    colta
    -0.49
     Mou
    -0.47
     webView
    -0.47
    InvalidProtocol
    -0.47
    ganie
    -0.46
    makan
    -0.46
    POSITIVE LOGITS
     dive
    1.31
     diving
    1.18
     dives
    1.14
     Dive
    1.11
     divers
    1.09
    dive
    1.03
     diver
    1.02
     scuba
    1.00
     Diving
    1.00
     dived
    1.00
    Activations Density 0.218%

    No Known Activations