© 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. 10705
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking actions in recipes

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

    Followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    technical documentation and notes

    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
     autorytatywna
    -0.48
    webElementXpaths
    -0.45
     Sentiment
    -0.43
    SBATCH
    -0.43
    GEBURTS
    -0.43
    ⓘ
    -0.42
    ніципа
    -0.42
    alus
    -0.41
    ⓧ
    -0.41
    Julia
    -0.41
    POSITIVE LOGITS
    richTextPanel
    0.48
    OpenHelper
    0.47
    LookAnd
    0.43
     NgModule
    0.40
     LoggerFactory
    0.39
     nonUne
    0.37
    setLayoutManager
    0.37
     BrowserModule
    0.35
    lutning
    0.35
    utilisons
    0.35
    Activations Density 0.180%

    No Known Activations