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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 111542
    Prev
    Next
    INDEX
    Explanations

    references to navigation-related concepts in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rptr
    -0.35
     Rptr
    -0.34
    providedIn
    -0.31
     nonUne
    -0.31
    hasMoreElements
    -0.30
    addAll
    -0.29
     far
    -0.29
     bad
    -0.28
     pe
    -0.28
    parametrize
    -0.28
    POSITIVE LOGITS
    NavigationView
    1.38
    navigation
    1.09
    NavController
    0.97
    StoryboardSegue
    0.85
    DrawerLayout
    0.81
     navigation
    0.78
    IntoConstraints
    0.78
    Navigation
    0.72
     NAVIGATION
    0.72
     Navigation
    0.71
    Activations Density 0.000%

    No Known Activations