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. 14-GEMMASCOPE-RES-16K
    6. 80
    Prev
    Next
    INDEX
    Explanations

    references to specific cases, legal documents, and their corresponding identifiers or record numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.95
    клопе
    -0.90
     незавершена
    -0.90
    RenderAtEndOf
    -0.88
     مشين
    -0.87
     beginnetje
    -0.86
    EndGlobalSection
    -0.86
    WriteTagHelper
    -0.85
    Diweddarwch
    -0.85
    setVerticalGroup
    -0.84
    POSITIVE LOGITS
     Reihe
    0.45
     vergeten
    0.45
    1
    0.43
     illetve
    0.43
    2
    0.42
     fråga
    0.41
     wymien
    0.40
     tovább
    0.40
    A
    0.40
     yanında
    0.40
    Activations Density 0.638%

    No Known Activations