© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 13053
    Prev
    Next
    INDEX
    Explanations

    instances of the word "android" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.68
    ́ng
    -0.67
    MessageTagHelper
    -0.66
    jsxFileName
    -0.66
    DIPSETTING
    -0.66
    CodedInputStream
    -0.65
    gink
    -0.65
    CppMethod
    -0.64
    queryInterface
    -0.64
    rån
    -0.63
    POSITIVE LOGITS
     android
    0.90
     Android
    0.68
    android
    0.63
     AppColors
    0.59
     anhyd
    0.57
    Android
    0.56
    uxxxx
    0.56
     Houſe
    0.54
     hla
    0.53
    INET
    0.53
    Activations Density 0.008%

    No Known Activations