© 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. 6119
    Prev
    Next
    INDEX
    Explanations

    conjugated forms of the verb "to have."

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

    Contractions with "'ve"

    np_acts-logits-general · gemini-2.0-flash

    I've followed by past participle

    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
    -0.43
    adds
    -0.42
    does
    -0.42
    says
    -0.40
    makes
    -0.40
    /**
    -0.40
    roads
    -0.40
    seems
    -0.40
    Says
    -0.40
    s
    -0.40
    POSITIVE LOGITS
     BrowserModule
    0.60
     Vie
    0.58
    ourite
    0.57
     previously
    0.55
    我已经
    0.55
     laſſen
    0.55
     ive
    0.54
    ivo
    0.52
     already
    0.52
     müſſen
    0.52
    Activations Density 0.107%

    No Known Activations