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. 25
    Prev
    Next
    INDEX
    Explanations

    references to characters or entities within a fictional universe

    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
    TagMode
    -0.64
    +:+
    -0.61
     JpaRepository
    -0.60
    RenderAtEndOf
    -0.58
    contentLoaded
    -0.57
     فريبيس
    -0.53
     französische
    -0.53
    iastes
    -0.53
     nî
    -0.52
    ">//
    -0.52
    POSITIVE LOGITS
     Vegeta
    1.04
     Goku
    1.02
     Gohan
    0.92
     Frie
    0.88
    Goku
    0.87
    Vegeta
    0.87
     Saiyan
    0.86
     Piccolo
    0.85
     goku
    0.83
     Trunks
    0.83
    Activations Density 0.331%

    No Known Activations