Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 107043
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "are" and its variations in different contexts

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

    you're or you are

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     monasterio
    -0.43
     numériques
    -0.42
     médié
    -0.41
     Grundlage
    -0.40
     Japão
    -0.39
     démocratique
    -0.39
     prochain
    -0.38
     féminine
    -0.38
     školy
    -0.38
     avenir
    -0.38
    POSITIVE LOGITS
     yourself
    0.85
    your
    0.81
    yourself
    0.78
    you
    0.77
     your
    0.77
    ſelf
    0.76
    AddTagHelper
    0.76
     Yourself
    0.74
    Your
    0.73
     yourselves
    0.71
    Activations Density 0.042%

    No Known Activations