© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 5463
    Prev
    Next
    INDEX
    Explanations

    references to Minnesota and its associated abbreviations or terms

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

    Minnesota or MNIST dataset abbreviations

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    BrowserModule
    -0.54
    TemporalType
    -0.48
    getResource
    -0.48
    ISHOP
    -0.47
    tolua
    -0.45
    charAt
    -0.45
    DESCRIP
    -0.45
    textTheme
    -0.44
     objets
    -0.44
     officinalis
    -0.44
    POSITIVE LOGITS
     MN
    1.90
    MN
    1.85
     mn
    1.65
    mn
    1.60
     Mn
    1.45
    Mn
    1.40
    mne
    0.98
     Minnesota
    0.95
    mnist
    0.94
     mne
    0.91
    Activations Density 0.017%

    No Known Activations