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. 2545
    Prev
    Next
    INDEX
    Explanations

    references to activities or attractions related to design and architecture

    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
    非常的
    -0.69
    🔰
    -0.69
    mektedir
    -0.68
    PerformLayout
    -0.66
     "..\..\..\
    -0.65
     старости
    -0.64
    orianCalendar
    -0.64
     skall
    -0.64
    Bardzo
    -0.63
    Serde
    -0.62
    POSITIVE LOGITS
     luxe
    0.68
     nods
    0.66
     celebs
    0.65
     staffers
    0.64
     enggak
    0.62
     newbies
    0.61
     übrigens
    0.60
     faves
    0.60
     nab
    0.60
     perfectos
    0.60
    Activations Density 0.252%

    No Known Activations