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. 1-GEMMASCOPE-RES-16K
    6. 13547
    Prev
    Next
    INDEX
    Explanations

    technical terms related to Android programming and activity lifecycle management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.61
    ribune
    -0.55
    nyttet
    -0.54
     menunggu
    -0.52
    boldmath
    -0.52
     stayed
    -0.51
    Fontes
    -0.49
    Pozdrawiam
    -0.48
     tár
    -0.48
     aprendido
    -0.47
    POSITIVE LOGITS
    InstanceState
    0.90
     neck
    0.68
    neck
    0.65
    hells
    0.62
     Checkout
    0.61
    出版年
    0.60
    migrationBuilder
    0.58
    iería
    0.58
    hoea
    0.58
     Differenti
    0.57
    Activations Density 1.736%

    No Known Activations