© 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. 8731
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people or entities

    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
     bas
    -0.45
     moments
    -0.38
     tired
    -0.36
     ener
    -0.36
     soci
    -0.35
    setminus
    -0.35
    طل
    -0.34
     metav
    -0.34
     بو
    -0.34
     حس
    -0.34
    POSITIVE LOGITS
     whereof
    0.85
    antaranya
    0.75
     duquel
    0.71
     antaranya
    0.70
    Билгалдахарш
    0.64
     hereof
    0.60
    MessageTagHelper
    0.60
     daarvan
    0.60
     שוליים
    0.60
     thereof
    0.58
    Activations Density 0.337%

    No Known Activations