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

    Neuronpedia

    Jacobian LensNEW
    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. 9694
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or entities involved in legal cases or discussions

    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
    Хьажоргаш
    -0.49
    HomeAsUpEnabled
    -0.47
    onedDateTime
    -0.43
     feroit
    -0.38
     burberry
    -0.37
    olybden
    -0.37
    /#/
    -0.37
     hwnd
    -0.37
     currentState
    -0.36
    AnchorStyles
    -0.36
    POSITIVE LOGITS
     Schmidt
    0.99
     Cohen
    0.90
     Garcia
    0.89
     Meyer
    0.88
     García
    0.84
     Álvarez
    0.84
     Pérez
    0.84
    Schmidt
    0.83
     Hoffmann
    0.82
     González
    0.82
    Activations Density 1.160%

    No Known Activations