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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13430
    Prev
    Next
    INDEX
    Explanations

    letters and their frequencies in various contexts

    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
     visibilidad
    -0.81
     sostenibilidad
    -0.79
     Infór
    -0.78
     perfección
    -0.77
     SALUD
    -0.74
     redacción
    -0.73
     contribución
    -0.73
     productividad
    -0.71
     adquisición
    -0.70
     inflación
    -0.70
    POSITIVE LOGITS
     F
    1.07
     C
    1.07
     D
    1.05
     G
    1.04
     M
    1.02
     B
    1.00
     T
    1.00
     V
    0.99
     H
    0.99
     S
    0.99
    Activations Density 0.978%

    No Known Activations