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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3626
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and its applications in various industries, particularly focusing on data management and automation

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

    business operations and technology

    np_acts-logits-general · gemini-2.0-flash

    business operations and digital transformation

    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
    titleMargin
    -0.41
     שוליים
    -0.36
    addGap
    -0.35
     disambiguazione
    -0.35
    outState
    -0.34
    rungsseite
    -0.34
     Mischung
    -0.32
     fábrica
    -0.32
    Kapcsolódó
    -0.32
     vuestros
    -0.31
    POSITIVE LOGITS
     digital
    0.59
     digitized
    0.53
     ChatGPT
    0.52
     RFID
    0.52
     vlog
    0.51
     digitally
    0.50
    APORE
    0.50
     drones
    0.50
     automating
    0.50
    ishman
    0.49
    Activations Density 0.312%

    No Known Activations