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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2417
    Prev
    Next
    INDEX
    Explanations

    references to data fetching and state management within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.81
    PreferredItem
    -0.79
     defaultstate
    -0.73
     Italijanski
    -0.72
     متعلقه
    -0.72
    httphttps
    -0.71
    DebuggerStep
    -0.70
     TextAppearance
    -0.70
    SharedDtor
    -0.69
    حوالہ
    -0.68
    POSITIVE LOGITS
     createSlice
    0.90
    redux
    0.75
     mapStateToProps
    0.69
     configureStore
    0.65
     combineReducers
    0.64
    DispatchToProps
    0.63
    mapStateToProps
    0.58
    propTypes
    0.56
    ngrx
    0.56
    Reducer
    0.56
    Activations Density 0.096%

    No Known Activations