© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-GEMMASCOPE-RES-16K
    11. 6196
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific method and data analysis

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

    Comes before gerunds/present participles

    np_acts-logits-general · gemini-2.0-flash

    when considering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.48
    HasIndex
    -0.47
     jspb
    -0.45
    __(/*!
    -0.44
    ngrx
    -0.44
    SequentialGroup
    -0.42
    WebElementEntity
    -0.41
    outWeight
    -0.41
    addWidget
    -0.40
    archiviato
    -0.40
    POSITIVE LOGITS
     Anſ
    0.54
     navideñas
    0.50
     navideños
    0.50
     damska
    0.47
     digitais
    0.47
     eléctricas
    0.46
     Wikiseite
    0.45
     ſche
    0.45
     wikipagina
    0.44
    AndroidJUnit
    0.44
    Activations Density 1.384%

    No Known Activations