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

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 13209
    Prev
    Next
    INDEX
    Explanations

    references to language and communication accents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.53
    /*---
    -0.43
    出版年
    -0.43
    LLocation
    -0.42
    CGRectMake
    -0.41
    UserScript
    -0.41
     كومونز
    -0.41
    StructEnd
    -0.40
    pdev
    -0.40
     AssemblyTitle
    -0.40
    POSITIVE LOGITS
     voice
    1.05
    voice
    0.90
     Stimme
    0.84
     voices
    0.80
     voix
    0.78
     VOICE
    0.77
     giọng
    0.75
     voz
    0.73
    Voice
    0.72
     Voice
    0.70
    Activations Density 0.089%

    No Known Activations