© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5866
    Prev
    Next
    INDEX
    Explanations

    specific names, terms, and phrases related to various fields including science, medicine, and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    richTextPanel
    -0.59
    webElementGuid
    -0.47
    ंदीखरीदारी
    -0.46
     HasFactory
    -0.46
     disambiguazione
    -0.45
    Numerade
    -0.39
     ffilmiau
    -0.39
    Personensuche
    -0.38
     universel
    -0.38
    dunk
    -0.38
    POSITIVE LOGITS
    jar
    0.81
    Cer
    0.78
     Cer
    0.73
     cho
    0.66
     cer
    0.65
     Jar
    0.64
    Jar
    0.63
    Cho
    0.61
     חיצוניים
    0.60
     Cho
    0.60
    Activations Density 1.235%

    No Known Activations