© 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. 3102
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to fractional calculus and differential equations

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

    "equation" or "problem" followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    differential equations

    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
    ########.
    -0.81
    Autoritní
    -0.72
    WebElementEntity
    -0.71
     iprot
    -0.67
     للاسماء
    -0.65
    
    -0.64
    CPtr
    -0.61
    GOTREF
    -0.59
    makeConstraints
    -0.59
    ApiModelProperty
    -0.58
    POSITIVE LOGITS
     problem
    0.49
     Problem
    0.38
    problem
    0.35
     problems
    0.35
     sorun
    0.34
    Problem
    0.34
     equation
    0.32
     problème
    0.32
     equations
    0.31
     Schrödinger
    0.30
    Activations Density 1.845%

    No Known Activations