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. 7450
    Prev
    Next
    INDEX
    Explanations

    keywords and function calls related to Android activity and fragment 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
     ngang
    -0.54
     cycle
    -0.51
     Cycle
    -0.50
     No
    -0.50
    piecze
    -0.48
     جه
    -0.47
     resistant
    -0.46
    {
    -0.46
     cycles
    -0.46
    PLING
    -0.45
    POSITIVE LOGITS
    addCriterion
    0.97
    InstanceState
    0.89
    PropertyChanging
    0.80
    LookAnd
    0.77
    AnchorStyles
    0.73
    RenderAtEndOf
    0.72
    matchCondition
    0.70
    })->
    0.68
    XMLSchema
    0.66
    AnimationsModule
    0.65
    Activations Density 1.965%

    No Known Activations