© 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. 7440
    Prev
    Next
    INDEX
    Explanations

    expressions of hard work and dedication

    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
     MatDialog
    -0.52
    ModelAdmin
    -0.50
     NSCoder
    -0.50
    ANTLR
    -0.47
    
    -0.46
    migrationBuilder
    -0.46
    ScopeManager
    -0.46
     DialogInterface
    -0.46
     flagged
    -0.44
     typelib
    -0.44
    POSITIVE LOGITS
     effort
    0.98
     efforts
    0.96
     Efforts
    0.93
     Effort
    0.91
    efforts
    0.91
    effort
    0.89
    Effort
    0.88
     esfuerzo
    0.88
    努力
    0.80
     esforço
    0.77
    Activations Density 0.098%

    No Known Activations