© 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. 2-GEMMASCOPE-RES-16K
    11. 4961
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perfección
    -0.69
     redacción
    -0.67
     orilla
    -0.66
     sostenibilidad
    -0.65
     contribución
    -0.63
     visibilidad
    -0.62
     escase
    -0.60
     elevación
    -0.60
     inflación
    -0.60
     competición
    -0.60
    POSITIVE LOGITS
     C
    1.36
     F
    1.34
     D
    1.33
     H
    1.33
     M
    1.31
     B
    1.30
     V
    1.27
     S
    1.24
     P
    1.23
     K
    1.23
    Activations Density 0.508%

    No Known Activations