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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-GEMMASCOPE-RES-16K
    6. 1899
    Prev
    Next
    INDEX
    Explanations

    references to the Android operating system and its related components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.73
    appé
    -0.68
     kasarigan
    -0.68
    oredCriteria
    -0.67
    MessageTagHelper
    -0.66
    queryInterface
    -0.66
    msgTypes
    -0.65
    sizeCache
    -0.64
     nonUne
    -0.60
    kenes
    -0.60
    POSITIVE LOGITS
     android
    1.39
     Android
    1.19
    android
    1.06
    Android
    0.99
    ANDROID
    0.90
    ROID
    0.78
     незавершена
    0.71
    PyExc
    0.70
     UnityEngine
    0.66
     الحره
    0.65
    Activations Density 0.009%

    No Known Activations