© 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. 3-GEMMASCOPE-RES-16K
    11. 5852
    Prev
    Next
    INDEX
    Explanations

    terms related to specific events, actions, or occurrences, particularly in legal and medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viitteet
    -0.57
    principalTable
    -0.48
    AsUp
    -0.48
    PyExc
    -0.48
     BorderSide
    -0.47
    WireFormatLite
    -0.45
    NameInMap
    -0.45
    ScopeManager
    -0.45
    appé
    -0.44
    Serde
    -0.44
    POSITIVE LOGITS
     Orth
    0.50
     Victor
    0.49
    
    0.49
    Orth
    0.47
     orth
    0.44
    ruptedException
    0.43
     sunset
    0.43
    Volatile
    0.42
     &___
    0.42
    tinyos
    0.42
    Activations Density 1.691%

    No Known Activations