© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14988
    Prev
    Next
    INDEX
    Explanations

    phrases related to navigation and different routes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    associated with routes or paths

    np_acts-logits-general · gemini-2.0-flash

    paths and routes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ReusableCell
    -0.57
     nakalista
    -0.47
     EconPapers
    -0.47
    getSystemService
    -0.46
    esez
    -0.46
    onAttach
    -0.46
     intervi
    -0.45
    MongoClient
    -0.45
    autoreleasepool
    -0.44
     flotante
    -0.44
    POSITIVE LOGITS
     path
    2.71
     paths
    2.52
    path
    2.31
     Path
    2.31
     route
    2.31
     pathway
    2.18
    Path
    2.17
     Paths
    2.15
     routes
    2.13
     pathways
    2.13
    Activations Density 0.443%

    No Known Activations