© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14485
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations, particularly names of places and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    iveau
    -0.61
    𓆱
    -0.55
    AutoScale
    -0.54
    Alger
    -0.54
     iNdEx
    -0.54
     ſehr
    -0.53
    𓂸
    -0.53
    PRESENT
    -0.52
    Hung
    -0.52
    issory
    -0.52
    POSITIVE LOGITS
    CppMethod
    0.45
     ***!
    0.42
    AndroidJUnit
    0.35
    IntoConstraints
    0.33
    QtGui
    0.32
    GEBURTS
    0.30
     Roskov
    0.30
    LayoutConstraint
    0.29
    Nationalité
    0.28
     monnaie
    0.28
    Activations Density 0.170%

    No Known Activations