© 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. 28-GEMMASCOPE-RES-16K
    6. 8985
    Prev
    Next
    INDEX
    Explanations

    mentions of Google and its associated services

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

    "Google" (variations and misspellings)

    np_acts-logits-general · gemini-2.0-flash

    google.com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    солю
    -0.38
     hand
    -0.30
     ra
    -0.30
     Kur
    -0.30
     tribal
    -0.30
     صح
    -0.30
     par
    -0.29
     preso
    -0.29
     Thor
    -0.29
     Hand
    -0.29
    POSITIVE LOGITS
     Google
    1.39
    Google
    1.35
     GOOGLE
    1.28
     google
    1.25
    GOOGLE
    1.16
    谷歌
    1.06
    google
    1.04
     goog
    0.95
     googled
    0.81
    goog
    0.79
    Activations Density 0.883%

    No Known Activations