© 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. 866
    Prev
    Next
    INDEX
    Explanations

    numerical data and sequences related to judicial cases

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

    Numbers followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    NASA CR reports

    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
    IntoConstraints
    -1.09
    tagHelperRunner
    -0.96
    AccessorTable
    -0.81
    WriteTagHelper
    -0.78
    
    -0.76
    ValueStyle
    -0.76
     ligiloj
    -0.75
    IsMutable
    -0.74
    GEBURTSDATUM
    -0.73
    脚注の使い方
    -0.73
    POSITIVE LOGITS
    2
    0.39
     maintien
    0.39
     honneur
    0.36
     espoir
    0.36
     épouse
    0.36
     Wahrheit
    0.35
    1
    0.35
     delà
    0.35
    ,
    0.35
    9
    0.35
    Activations Density 1.371%

    No Known Activations