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. 3-GEMMASCOPE-RES-16K
    6. 12746
    Prev
    Next
    INDEX
    Explanations

    references to the Android operating system and related platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.89
    gink
    -0.87
    /*
    -0.78
    ostante
    -0.78
     defaultstate
    -0.75
    قایناق‌لار
    -0.74
     ObjectMapper
    -0.73
    Demografia
    -0.73
    ]")]
    -0.73
     FIM
    -0.73
    POSITIVE LOGITS
     Android
    3.07
    Android
    2.87
     android
    2.46
    android
    2.14
    ANDROID
    1.93
    安卓
    1.46
     安卓
    1.40
     اندروید
    1.34
    ROID
    1.33
     iOS
    1.27
    Activations Density 0.037%

    No Known Activations