© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 842
    Prev
    Next
    INDEX
    Explanations

    titles and nicknames related to places, people, or concepts

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

    Appellations, nicknames, or aliases

    np_acts-logits-general · gemini-2.0-flash

    epithets or alternative names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.51
    دانشنامهٔ
    -0.47
    ArrowToggle
    -0.47
     Autorisations
    -0.45
     abstracta
    -0.39
     queſta
    -0.38
    قایناق‌لار
    -0.37
    vivencia
    -0.37
    Décès
    -0.37
     Autorizaciones
    -0.36
    POSITIVE LOGITS
     nicknamed
    0.80
     dubbed
    0.71
     nickname
    0.60
     nicknames
    0.56
    被称为
    0.52
     “
    0.46
     nazy
    0.45
     disebut
    0.45
     referred
    0.45
    と呼ば
    0.45
    Activations Density 0.190%

    No Known Activations