© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12497
    Prev
    Next
    INDEX
    Explanations

    terms related to the Android operating system and its development environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gink
    -0.68
     Xunit
    -0.68
    fortawesome
    -0.65
    ]")]
    -0.65
     ObjectMapper
    -0.65
    +#+#
    -0.64
    Lynne
    -0.64
     viață
    -0.63
    WebVitals
    -0.61
     connais
    -0.60
    POSITIVE LOGITS
     Android
    1.72
    Android
    1.54
     android
    1.39
    android
    1.26
    ANDROID
    1.17
     Andri
    1.04
     安卓
    0.95
    ROID
    0.93
     Andro
    0.89
    安卓
    0.87
    Activations Density 0.053%

    No Known Activations