© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12572
    Prev
    Next
    INDEX
    Explanations

    configuration settings related to server rules and mappings

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    CSS rules and selectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    ReusableCell
    -0.65
    脚注の使い方
    -0.65
    principalTable
    -0.63
    PerformLayout
    -0.63
    setVerticalGroup
    -0.62
    WaitGroup
    -0.59
    bootstrapcdn
    -0.56
     Biôgrafia
    -0.54
    OrNil
    -0.52
     Wiktionnaire
    -0.52
    POSITIVE LOGITS
    stylers
    0.54
     conditions
    0.40
    ByExample
    0.39
    \\\
    0.35
    ffer
    0.34
     voorwaarden
    0.33
    joni
    0.33
    Ứ
    0.32
    taget
    0.32
     General
    0.32
    Activations Density 0.904%

    No Known Activations