© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6346
    Prev
    Next
    INDEX
    Explanations

    numerical values related to scientific measurements or data

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

    Numbers followed by comma, then more numbers

    np_acts-logits-general · gemini-2.0-flash

    ranges and numbers

    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
    ListItemIcon
    -0.47
     nî
    -0.44
    دانشنامهٔ
    -0.43
     cerâmica
    -0.40
     moeder
    -0.40
    蚪
    -0.40
     Bewußt
    -0.39
     Italijani
    -0.39
    MLLoader
    -0.38
     bandeira
    -0.38
    POSITIVE LOGITS
     autorytatywna
    0.49
    Portale
    0.48
     betweenstory
    0.45
    Abit
    0.42
     snippetHide
    0.42
     embri
    0.40
     difer
    0.40
    Geplaatst
    0.38
    GeneratedMessage
    0.37
     ویکی‌پدی
    0.36
    Activations Density 1.301%

    No Known Activations