© 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. 14893
    Prev
    Next
    INDEX
    Explanations

    instances of the word "path" in various contexts

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

    The token "Path" or "path"

    np_acts-logits-general · gemini-2.0-flash

    path to locations

    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
    windowFixed
    -0.74
     HasFactory
    -0.67
    ChildScrollView
    -0.64
     ſmall
    -0.64
    toHexString
    -0.60
     reaſon
    -0.60
     pleaſure
    -0.58
    ſelf
    -0.58
     ſame
    -0.58
     uſed
    -0.57
    POSITIVE LOGITS
    WAY
    0.79
    way
    0.77
     Paths
    0.73
    ways
    0.73
     paths
    0.71
    finder
    0.71
     ways
    0.71
     getPath
    0.70
    finding
    0.68
    Ways
    0.66
    Activations Density 0.082%

    No Known Activations