Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 1854
    Prev
    Next
    INDEX
    Explanations

    references to various forms of media and media organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.77
     Gump
    -0.70
     mof
    -0.68
    expandindo
    -0.67
     Cumber
    -0.64
     Bumble
    -0.63
     Sight
    -0.63
     Gele
    -0.62
    Vist
    -0.62
    GetKeyDown
    -0.62
    POSITIVE LOGITS
    MEDIA
    1.31
     MEDIA
    1.30
     Media
    1.27
     media
    1.26
     medias
    1.24
    Media
    1.14
    media
    1.08
     MediaType
    1.00
     Medien
    0.99
    medi
    0.93
    Activations Density 0.113%

    No Known Activations