© 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. 31-GEMMASCOPE-RES-16K
    11. 9684
    Prev
    Next
    INDEX
    Explanations

    tokens related to non-English characters or symbols, likely focusing on specific languages or scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    non-Latin script characters and foreign language text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.32
    forChild
    -0.32
    PerformLayout
    -0.31
     AssemblyProduct
    -0.31
     Truman
    -0.30
     Canaria
    -0.29
    ariConfig
    -0.29
    LabelTagHelper
    -0.29
    addGap
    -0.28
     Jamaican
    -0.28
    POSITIVE LOGITS
     Myanmar
    1.15
    Myanmar
    1.04
     Burmese
    0.97
     Burma
    0.86
     Aung
    0.85
    aung
    0.78
     Rohing
    0.70
    缅
    0.68
     Rango
    0.64
    Zaw
    0.64
    Activations Density 0.053%

    No Known Activations