© 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. 10127
    Prev
    Next
    INDEX
    Explanations

    negations and terms related to exclusion or absence in contexts discussing policies or contractual obligations

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

    "non", "not", "without"

    np_acts-logits-general · gemini-2.0-flash

    negation words like non, not, without

    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
    enderror
    -0.39
     '{@
    -0.37
    AnchorStyles
    -0.36
     overras
    -0.36
     meeste
    -0.35
     raiſ
    -0.35
    heavy
    -0.35
    viola
    -0.34
    Rit
    -0.34
     testSet
    -0.34
    POSITIVE LOGITS
     disambiguazione
    0.56
     propOrder
    0.50
     Himo
    0.50
     OMITTED
    0.45
    Források
    0.45
    脚注の使い方
    0.45
     Tenggara
    0.42
    лтемелер
    0.42
     cherchés
    0.41
    тербург
    0.41
    Activations Density 0.498%

    No Known Activations