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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 10893
    Prev
    Next
    INDEX
    Explanations

    references to observable patterns and bindings in programming contexts, particularly related to Knockout.js frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.61
    +:+
    -0.61
    djangoproject
    -0.61
    IonicModule
    -0.60
     defaultstate
    -0.60
    extAlignment
    -0.57
    ChildScrollView
    -0.56
    PreferredItem
    -0.56
    NgModule
    -0.56
    RequiresApi
    -0.55
    POSITIVE LOGITS
     ViewModel
    0.70
    ViewModel
    0.63
     estekak
    0.62
    MutableLiveData
    0.61
     createState
    0.61
    MLLoader
    0.59
     viewModel
    0.58
     models
    0.57
     "..\..\
    0.57
     "..\..\..\
    0.55
    Activations Density 0.190%

    No Known Activations